Merge branch 'dev' into dev

CHANGELOG.md

@@ -1,3 +1,8 @@
+## 1.9.4
+
+### Bug Fixes:
+*  pin setuptools version to fix the startup error ([#15882](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15882)) 
+
 ## 1.9.3
 
 ### Bug Fixes:

configs/alt-diffusion-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/alt-diffusion-m18-inference.yaml

@@ -41,7 +41,7 @@ model:
         use_linear_in_transformer: True
         transformer_depth: 1
         context_dim: 1024
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/instruct-pix2pix.yaml

@@ -45,7 +45,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/sd_xl_inpaint.yaml

@@ -21,7 +21,7 @@ model:
       params:
         adm_in_channels: 2816
         num_classes: sequential
-        use_checkpoint: True
+        use_checkpoint: False
         in_channels: 9
         out_channels: 4
         model_channels: 320

configs/v1-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

configs/v1-inpainting-inference.yaml

@@ -40,7 +40,7 @@ model:
         use_spatial_transformer: True
         transformer_depth: 1
         context_dim: 768
-        use_checkpoint: True
+        use_checkpoint: False
         legacy: False
 
     first_stage_config:

extensions-builtin/Lora/networks.py

@@ -260,6 +260,16 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
 
     loaded_networks.clear()
 
+    unavailable_networks = []
+    for name in names:
+        if name.lower() in forbidden_network_aliases and available_networks.get(name) is None:
+            unavailable_networks.append(name)
+        elif available_network_aliases.get(name) is None:
+            unavailable_networks.append(name)
+
+    if unavailable_networks:
+        update_available_networks_by_names(unavailable_networks)
+
     networks_on_disk = [available_networks.get(name, None) if name.lower() in forbidden_network_aliases else available_network_aliases.get(name, None) for name in names]
     if any(x is None for x in networks_on_disk):
         list_available_networks()
@@ -378,13 +388,18 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
         self.network_weights_backup = weights_backup
 
     bias_backup = getattr(self, "network_bias_backup", None)
-    if bias_backup is None:
+    if bias_backup is None and wanted_names != ():
         if isinstance(self, torch.nn.MultiheadAttention) and self.out_proj.bias is not None:
             bias_backup = self.out_proj.bias.to(devices.cpu, copy=True)
         elif getattr(self, 'bias', None) is not None:
             bias_backup = self.bias.to(devices.cpu, copy=True)
         else:
             bias_backup = None
+
+        # Unlike weight which always has value, some modules don't have bias.
+        # Only report if bias is not None and current bias are not unchanged.
+        if bias_backup is not None and current_names != ():
+            raise RuntimeError("no backup bias found and current bias are not unchanged")
         self.network_bias_backup = bias_backup
 
     if current_names != wanted_names:
@@ -566,22 +581,16 @@ def network_MultiheadAttention_load_state_dict(self, *args, **kwargs):
     return originals.MultiheadAttention_load_state_dict(self, *args, **kwargs)
 
 
-def list_available_networks():
+def process_network_files(names: list[str] | None = None):
-    available_networks.clear()
-    available_network_aliases.clear()
-    forbidden_network_aliases.clear()
-    available_network_hash_lookup.clear()
-    forbidden_network_aliases.update({"none": 1, "Addams": 1})
-
-    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
-
     candidates = list(shared.walk_files(shared.cmd_opts.lora_dir, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
     candidates += list(shared.walk_files(shared.cmd_opts.lyco_dir_backcompat, allowed_extensions=[".pt", ".ckpt", ".safetensors"]))
     for filename in candidates:
         if os.path.isdir(filename):
             continue
-
         name = os.path.splitext(os.path.basename(filename))[0]
+        # if names is provided, only load networks with names in the list
+        if names and name not in names:
+            continue
         try:
             entry = network.NetworkOnDisk(name, filename)
         except OSError:  # should catch FileNotFoundError and PermissionError etc.
@@ -597,6 +606,22 @@ def list_available_networks():
         available_network_aliases[entry.alias] = entry
 
 
+def update_available_networks_by_names(names: list[str]):
+    process_network_files(names)
+
+
+def list_available_networks():
+    available_networks.clear()
+    available_network_aliases.clear()
+    forbidden_network_aliases.clear()
+    available_network_hash_lookup.clear()
+    forbidden_network_aliases.update({"none": 1, "Addams": 1})
+
+    os.makedirs(shared.cmd_opts.lora_dir, exist_ok=True)
+
+    process_network_files()
+
+
 re_network_name = re.compile(r"(.*)\s*\([0-9a-fA-F]+\)")
 
 

extensions-builtin/Lora/ui_extra_networks_lora.py

@@ -60,7 +60,7 @@ class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
         else:
             sd_version = lora_on_disk.sd_version
 
-        if shared.opts.lora_show_all or not enable_filter:
+        if shared.opts.lora_show_all or not enable_filter or not shared.sd_model:
             pass
         elif sd_version == network.SdVersion.Unknown:
             model_version = network.SdVersion.SDXL if shared.sd_model.is_sdxl else network.SdVersion.SD2 if shared.sd_model.is_sd2 else network.SdVersion.SD1

extensions-builtin/hypertile/scripts/hypertile_script.py

@@ -1,6 +1,5 @@
 import hypertile
 from modules import scripts, script_callbacks, shared
-from scripts.hypertile_xyz import add_axis_options
 
 
 class ScriptHypertile(scripts.Script):
@@ -93,7 +92,6 @@ def on_ui_settings():
         "hypertile_max_depth_unet": shared.OptionInfo(3, "Hypertile U-Net max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile U-Net max depth").info("larger = more neural network layers affected; minor effect on performance"),
         "hypertile_max_tile_unet": shared.OptionInfo(256, "Hypertile U-Net max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile U-Net max tile size").info("larger = worse performance"),
         "hypertile_swap_size_unet": shared.OptionInfo(3, "Hypertile U-Net swap size", gr.Slider, {"minimum": 0, "maximum": 64, "step": 1}, infotext="Hypertile U-Net swap size"),
-
         "hypertile_enable_vae": shared.OptionInfo(False, "Enable Hypertile VAE", infotext="Hypertile VAE").info("minimal change in the generated picture"),
         "hypertile_max_depth_vae": shared.OptionInfo(3, "Hypertile VAE max depth", gr.Slider, {"minimum": 0, "maximum": 3, "step": 1}, infotext="Hypertile VAE max depth"),
         "hypertile_max_tile_vae": shared.OptionInfo(128, "Hypertile VAE max tile size", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}, infotext="Hypertile VAE max tile size"),
@@ -105,5 +103,20 @@ def on_ui_settings():
         shared.opts.add_option(name, opt)
 
 
+def add_axis_options():
+    xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
+    xyz_grid.axis_options.extend([
+        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, xyz_grid.apply_override('hypertile_enable_unet_secondpass', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_unet"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] Unet Max Depth'), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_unet"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] Unet Max Tile Size')),
+        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_unet"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] Unet Swap Size')),
+        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, xyz_grid.apply_override('hypertile_enable_vae', boolean=True), choices=xyz_grid.boolean_choice(reverse=True)),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, xyz_grid.apply_override("hypertile_max_depth_vae"), confirm=xyz_grid.confirm_range(0, 3, '[Hypertile] VAE Max Depth'), choices=lambda: [str(x) for x in range(4)]),
+        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, xyz_grid.apply_override("hypertile_max_tile_vae"), confirm=xyz_grid.confirm_range(0, 512, '[Hypertile] VAE Max Tile Size')),
+        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, xyz_grid.apply_override("hypertile_swap_size_vae"), confirm=xyz_grid.confirm_range(0, 64, '[Hypertile] VAE Swap Size')),
+    ])
+
+
 script_callbacks.on_ui_settings(on_ui_settings)
 script_callbacks.on_before_ui(add_axis_options)

extensions-builtin/hypertile/scripts/hypertile_xyz.py

@@ -1,51 +0,0 @@
-from modules import scripts
-from modules.shared import opts
-
-xyz_grid = [x for x in scripts.scripts_data if x.script_class.__module__ == "xyz_grid.py"][0].module
-
-def int_applier(value_name:str, min_range:int = -1, max_range:int = -1):
-    """
-    Returns a function that applies the given value to the given value_name in opts.data.
-    """
-    def validate(value_name:str, value:str):
-        value = int(value)
-        # validate value
-        if not min_range == -1:
-            assert value >= min_range, f"Value {value} for {value_name} must be greater than or equal to {min_range}"
-        if not max_range == -1:
-            assert value <= max_range, f"Value {value} for {value_name} must be less than or equal to {max_range}"
-    def apply_int(p, x, xs):
-        validate(value_name, x)
-        opts.data[value_name] = int(x)
-    return apply_int
-
-def bool_applier(value_name:str):
-    """
-    Returns a function that applies the given value to the given value_name in opts.data.
-    """
-    def validate(value_name:str, value:str):
-        assert value.lower() in ["true", "false"], f"Value {value} for {value_name} must be either true or false"
-    def apply_bool(p, x, xs):
-        validate(value_name, x)
-        value_boolean = x.lower() == "true"
-        opts.data[value_name] = value_boolean
-    return apply_bool
-
-def add_axis_options():
-    extra_axis_options = [
-        xyz_grid.AxisOption("[Hypertile] Unet First pass Enabled", str, bool_applier("hypertile_enable_unet"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] Unet Second pass Enabled", str, bool_applier("hypertile_enable_unet_secondpass"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] Unet Max Depth", int, int_applier("hypertile_max_depth_unet", 0, 3), choices=lambda: [str(x) for x in range(4)]),
-        xyz_grid.AxisOption("[Hypertile] Unet Max Tile Size", int, int_applier("hypertile_max_tile_unet", 0, 512)),
-        xyz_grid.AxisOption("[Hypertile] Unet Swap Size", int, int_applier("hypertile_swap_size_unet", 0, 64)),
-        xyz_grid.AxisOption("[Hypertile] VAE Enabled", str, bool_applier("hypertile_enable_vae"), choices=xyz_grid.boolean_choice(reverse=True)),
-        xyz_grid.AxisOption("[Hypertile] VAE Max Depth", int, int_applier("hypertile_max_depth_vae", 0, 3), choices=lambda: [str(x) for x in range(4)]),
-        xyz_grid.AxisOption("[Hypertile] VAE Max Tile Size", int, int_applier("hypertile_max_tile_vae", 0, 512)),
-        xyz_grid.AxisOption("[Hypertile] VAE Swap Size", int, int_applier("hypertile_swap_size_vae", 0, 64)),
-    ]
-    set_a = {opt.label for opt in xyz_grid.axis_options}
-    set_b = {opt.label for opt in extra_axis_options}
-    if set_a.intersection(set_b):
-        return
-
-    xyz_grid.axis_options.extend(extra_axis_options)

extensions-builtin/soft-inpainting/scripts/soft_inpainting.py

@@ -3,6 +3,7 @@ import gradio as gr
 import math
 from modules.ui_components import InputAccordion
 import modules.scripts as scripts
+from modules.torch_utils import float64
 
 
 class SoftInpaintingSettings:
@@ -79,13 +80,11 @@ def latent_blend(settings, a, b, t):
 
     # Calculate the magnitude of the interpolated vectors. (We will remove this magnitude.)
     # 64-bit operations are used here to allow large exponents.
-    current_magnitude = torch.norm(image_interp, p=2, dim=1, keepdim=True).to(torch.float64).add_(0.00001)
+    current_magnitude = torch.norm(image_interp, p=2, dim=1, keepdim=True).to(float64(image_interp)).add_(0.00001)
 
     # Interpolate the powered magnitudes, then un-power them (bring them back to a power of 1).
-    a_magnitude = torch.norm(a, p=2, dim=1, keepdim=True).to(torch.float64).pow_(
+    a_magnitude = torch.norm(a, p=2, dim=1, keepdim=True).to(float64(a)).pow_(settings.inpaint_detail_preservation) * one_minus_t3
-        settings.inpaint_detail_preservation) * one_minus_t3
+    b_magnitude = torch.norm(b, p=2, dim=1, keepdim=True).to(float64(b)).pow_(settings.inpaint_detail_preservation) * t3
-    b_magnitude = torch.norm(b, p=2, dim=1, keepdim=True).to(torch.float64).pow_(
-        settings.inpaint_detail_preservation) * t3
     desired_magnitude = a_magnitude
     desired_magnitude.add_(b_magnitude).pow_(1 / settings.inpaint_detail_preservation)
     del a_magnitude, b_magnitude, t3, one_minus_t3

javascript/ui.js

@@ -337,8 +337,8 @@ onOptionsChanged(function() {
 let txt2img_textarea, img2img_textarea = undefined;
 
 function restart_reload() {
+    document.body.style.backgroundColor = "var(--background-fill-primary)";
     document.body.innerHTML = '<h1 style="font-family:monospace;margin-top:20%;color:lightgray;text-align:center;">Reloading...</h1>';
-
     var requestPing = function() {
         requestGet("./internal/ping", {}, function(data) {
             location.reload();

modules/api/api.py

@@ -438,15 +438,19 @@ class Api:
         self.apply_infotext(txt2imgreq, "txt2img", script_runner=script_runner, mentioned_script_args=infotext_script_args)
 
         selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner)
+        sampler, scheduler = sd_samplers.get_sampler_and_scheduler(txt2imgreq.sampler_name or txt2imgreq.sampler_index, txt2imgreq.scheduler)
 
         populate = txt2imgreq.copy(update={  # Override __init__ params
-            "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index),
+            "sampler_name": validate_sampler_name(sampler),
             "do_not_save_samples": not txt2imgreq.save_images,
             "do_not_save_grid": not txt2imgreq.save_images,
         })
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
+        if not populate.scheduler and scheduler != "Automatic":
+            populate.scheduler = scheduler
+
         args = vars(populate)
         args.pop('script_name', None)
         args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them
@@ -502,9 +506,10 @@ class Api:
         self.apply_infotext(img2imgreq, "img2img", script_runner=script_runner, mentioned_script_args=infotext_script_args)
 
         selectable_scripts, selectable_script_idx = self.get_selectable_script(img2imgreq.script_name, script_runner)
+        sampler, scheduler = sd_samplers.get_sampler_and_scheduler(img2imgreq.sampler_name or img2imgreq.sampler_index, img2imgreq.scheduler)
 
         populate = img2imgreq.copy(update={  # Override __init__ params
-            "sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index),
+            "sampler_name": validate_sampler_name(sampler),
             "do_not_save_samples": not img2imgreq.save_images,
             "do_not_save_grid": not img2imgreq.save_images,
             "mask": mask,
@@ -512,6 +517,9 @@ class Api:
         if populate.sampler_name:
             populate.sampler_index = None  # prevent a warning later on
 
+        if not populate.scheduler and scheduler != "Automatic":
+            populate.scheduler = scheduler
+
         args = vars(populate)
         args.pop('include_init_images', None)  # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine.
         args.pop('script_name', None)

modules/cmd_args.py

@@ -41,7 +41,7 @@ parser.add_argument("--lowvram", action='store_true', help="enable stable diffus
 parser.add_argument("--lowram", action='store_true', help="load stable diffusion checkpoint weights to VRAM instead of RAM")
 parser.add_argument("--always-batch-cond-uncond", action='store_true', help="does not do anything")
 parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
-parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
+parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "half", "autocast"], default="autocast")
 parser.add_argument("--upcast-sampling", action='store_true', help="upcast sampling. No effect with --no-half. Usually produces similar results to --no-half with better performance while using less memory.")
 parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site")
 parser.add_argument("--ngrok", type=str, help="ngrok authtoken, alternative to gradio --share", default=None)

modules/devices.py

@@ -114,6 +114,9 @@ errors.run(enable_tf32, "Enabling TF32")
 
 cpu: torch.device = torch.device("cpu")
 fp8: bool = False
+# Force fp16 for all models in inference. No casting during inference.
+# This flag is controlled by "--precision half" command line arg.
+force_fp16: bool = False
 device: torch.device = None
 device_interrogate: torch.device = None
 device_gfpgan: torch.device = None
@@ -127,6 +130,8 @@ unet_needs_upcast = False
 
 
 def cond_cast_unet(input):
+    if force_fp16:
+        return input.to(torch.float16)
     return input.to(dtype_unet) if unet_needs_upcast else input
 
 
@@ -206,6 +211,11 @@ def autocast(disable=False):
     if disable:
         return contextlib.nullcontext()
 
+    if force_fp16:
+        # No casting during inference if force_fp16 is enabled.
+        # All tensor dtype conversion happens before inference.
+        return contextlib.nullcontext()
+
     if fp8 and device==cpu:
         return torch.autocast("cpu", dtype=torch.bfloat16, enabled=True)
 
@@ -269,3 +279,17 @@ def first_time_calculation():
     x = torch.zeros((1, 1, 3, 3)).to(device, dtype)
     conv2d = torch.nn.Conv2d(1, 1, (3, 3)).to(device, dtype)
     conv2d(x)
+
+
+def force_model_fp16():
+    """
+    ldm and sgm has modules.diffusionmodules.util.GroupNorm32.forward, which
+    force conversion of input to float32. If force_fp16 is enabled, we need to
+    prevent this casting.
+    """
+    assert force_fp16
+    import sgm.modules.diffusionmodules.util as sgm_util
+    import ldm.modules.diffusionmodules.util as ldm_util
+    sgm_util.GroupNorm32 = torch.nn.GroupNorm
+    ldm_util.GroupNorm32 = torch.nn.GroupNorm
+    print("ldm/sgm GroupNorm32 replaced with normal torch.nn.GroupNorm due to `--precision half`.")

modules/extensions.py

@@ -191,8 +191,9 @@ class Extension:
 
     def check_updates(self):
         repo = Repo(self.path)
+        branch_name = f'{repo.remote().name}/{self.branch}'
         for fetch in repo.remote().fetch(dry_run=True):
-            if self.branch and fetch.name != f'{repo.remote().name}/{self.branch}':
+            if self.branch and fetch.name != branch_name:
                 continue
             if fetch.flags != fetch.HEAD_UPTODATE:
                 self.can_update = True
@@ -200,7 +201,7 @@ class Extension:
                 return
 
         try:
-            origin = repo.rev_parse('origin')
+            origin = repo.rev_parse(branch_name)
             if repo.head.commit != origin:
                 self.can_update = True
                 self.status = "behind HEAD"
@@ -213,8 +214,10 @@ class Extension:
         self.can_update = False
         self.status = "latest"
 
-    def fetch_and_reset_hard(self, commit='origin'):
+    def fetch_and_reset_hard(self, commit=None):
         repo = Repo(self.path)
+        if commit is None:
+            commit = f'{repo.remote().name}/{self.branch}'
         # Fix: `error: Your local changes to the following files would be overwritten by merge`,
         # because WSL2 Docker set 755 file permissions instead of 644, this results to the error.
         repo.git.fetch(all=True)

modules/images.py

@@ -653,7 +653,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     # WebP and JPG formats have maximum dimension limits of 16383 and 65535 respectively. switch to PNG which has a much higher limit
     if (image.height > 65535 or image.width > 65535) and extension.lower() in ("jpg", "jpeg") or (image.height > 16383 or image.width > 16383) and extension.lower() == "webp":
         print('Image dimensions too large; saving as PNG')
-        extension = ".png"
+        extension = "png"
 
     if save_to_dirs is None:
         save_to_dirs = (grid and opts.grid_save_to_dirs) or (not grid and opts.save_to_dirs and not no_prompt)

modules/img2img.py

@@ -17,11 +17,14 @@ from modules.ui import plaintext_to_html
 import modules.scripts
 
 
-def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
+def process_batch(p, input, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
     output_dir = output_dir.strip()
     processing.fix_seed(p)
 
-    batch_images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
+    if isinstance(input, str):
+        batch_images = list(shared.walk_files(input, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
+    else:
+        batch_images = [os.path.abspath(x.name) for x in input]
 
     is_inpaint_batch = False
     if inpaint_mask_dir:
@@ -146,7 +149,7 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal
     return batch_results
 
 
-def img2img(id_task: str, request: gr.Request, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, *args):
+def img2img(id_task: str, request: gr.Request, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, mask_blur: int, mask_alpha: float, inpainting_fill: int, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, img2img_batch_source_type: str, img2img_batch_upload: list, *args):
     override_settings = create_override_settings_dict(override_settings_texts)
 
     is_batch = mode == 5
@@ -221,8 +224,15 @@ def img2img(id_task: str, request: gr.Request, mode: int, prompt: str, negative_
 
     with closing(p):
         if is_batch:
-            assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
+            if img2img_batch_source_type == "upload":
-            processed = process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
+                assert isinstance(img2img_batch_upload, list) and img2img_batch_upload
+                output_dir = ""
+                inpaint_mask_dir = ""
+                png_info_dir = img2img_batch_png_info_dir if not shared.cmd_opts.hide_ui_dir_config else ""
+                processed = process_batch(p, img2img_batch_upload, output_dir, inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=png_info_dir)
+            else: # "from dir"
+                assert not shared.cmd_opts.hide_ui_dir_config, "Launched with --hide-ui-dir-config, batch img2img disabled"
+                processed = process_batch(p, img2img_batch_input_dir, img2img_batch_output_dir, img2img_batch_inpaint_mask_dir, args, to_scale=selected_scale_tab == 1, scale_by=scale_by, use_png_info=img2img_batch_use_png_info, png_info_props=img2img_batch_png_info_props, png_info_dir=img2img_batch_png_info_dir)
 
             if processed is None:
                 processed = Processed(p, [], p.seed, "")

modules/processing.py

@@ -115,20 +115,17 @@ def txt2img_image_conditioning(sd_model, x, width, height):
         return x.new_zeros(x.shape[0], 2*sd_model.noise_augmentor.time_embed.dim, dtype=x.dtype, device=x.device)
 
     else:
-        sd = sd_model.model.state_dict()
+        if getattr(sd_model.model, "is_sdxl_inpaint", False):
-        diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
+            # The "masked-image" in this case will just be all 0.5 since the entire image is masked.
-        if diffusion_model_input is not None:
+            image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5
-            if diffusion_model_input.shape[1] == 9:
+            image_conditioning = images_tensor_to_samples(image_conditioning,
-                # The "masked-image" in this case will just be all 0.5 since the entire image is masked.
+                                                            approximation_indexes.get(opts.sd_vae_encode_method))
-                image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5
-                image_conditioning = images_tensor_to_samples(image_conditioning,
-                                                              approximation_indexes.get(opts.sd_vae_encode_method))
 
-                # Add the fake full 1s mask to the first dimension.
+            # Add the fake full 1s mask to the first dimension.
-                image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+            image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
-                image_conditioning = image_conditioning.to(x.dtype)
+            image_conditioning = image_conditioning.to(x.dtype)
 
-                return image_conditioning
+            return image_conditioning
 
         # Dummy zero conditioning if we're not using inpainting or unclip models.
         # Still takes up a bit of memory, but no encoder call.
@@ -238,11 +235,6 @@ class StableDiffusionProcessing:
             self.styles = []
 
         self.sampler_noise_scheduler_override = None
-        self.s_min_uncond = self.s_min_uncond if self.s_min_uncond is not None else opts.s_min_uncond
-        self.s_churn = self.s_churn if self.s_churn is not None else opts.s_churn
-        self.s_tmin = self.s_tmin if self.s_tmin is not None else opts.s_tmin
-        self.s_tmax = (self.s_tmax if self.s_tmax is not None else opts.s_tmax) or float('inf')
-        self.s_noise = self.s_noise if self.s_noise is not None else opts.s_noise
 
         self.extra_generation_params = self.extra_generation_params or {}
         self.override_settings = self.override_settings or {}
@@ -259,6 +251,13 @@ class StableDiffusionProcessing:
         self.cached_uc = StableDiffusionProcessing.cached_uc
         self.cached_c = StableDiffusionProcessing.cached_c
 
+    def fill_fields_from_opts(self):
+        self.s_min_uncond = self.s_min_uncond if self.s_min_uncond is not None else opts.s_min_uncond
+        self.s_churn = self.s_churn if self.s_churn is not None else opts.s_churn
+        self.s_tmin = self.s_tmin if self.s_tmin is not None else opts.s_tmin
+        self.s_tmax = (self.s_tmax if self.s_tmax is not None else opts.s_tmax) or float('inf')
+        self.s_noise = self.s_noise if self.s_noise is not None else opts.s_noise
+
     @property
     def sd_model(self):
         return shared.sd_model
@@ -390,11 +389,8 @@ class StableDiffusionProcessing:
         if self.sampler.conditioning_key == "crossattn-adm":
             return self.unclip_image_conditioning(source_image)
 
-        sd = self.sampler.model_wrap.inner_model.model.state_dict()
+        if getattr(self.sampler.model_wrap.inner_model.model, "is_sdxl_inpaint", False):
-        diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
+            return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
-        if diffusion_model_input is not None:
-            if diffusion_model_input.shape[1] == 9:
-                return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
 
         # Dummy zero conditioning if we're not using inpainting or depth model.
         return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
@@ -569,7 +565,7 @@ class Processed:
         self.all_negative_prompts = all_negative_prompts or p.all_negative_prompts or [self.negative_prompt]
         self.all_seeds = all_seeds or p.all_seeds or [self.seed]
         self.all_subseeds = all_subseeds or p.all_subseeds or [self.subseed]
-        self.infotexts = infotexts or [info]
+        self.infotexts = infotexts or [info] * len(images_list)
         self.version = program_version()
 
     def js(self):
@@ -794,7 +790,6 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr,
         "Init image hash": getattr(p, 'init_img_hash', None),
         "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
-        "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
         "Tiling": "True" if p.tiling else None,
         **p.extra_generation_params,
         "Version": program_version() if opts.add_version_to_infotext else None,
@@ -842,6 +837,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
 
         sd_models.apply_token_merging(p.sd_model, p.get_token_merging_ratio())
 
+        # backwards compatibility, fix sampler and scheduler if invalid
+        sd_samplers.fix_p_invalid_sampler_and_scheduler(p)
+
         res = process_images_inner(p)
 
     finally:
@@ -890,6 +888,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
     modules.sd_hijack.model_hijack.apply_circular(p.tiling)
     modules.sd_hijack.model_hijack.clear_comments()
 
+    p.fill_fields_from_opts()
     p.setup_prompts()
 
     if isinstance(seed, list):

modules/sd_hijack_optimizations.py

@@ -486,7 +486,8 @@ def xformers_attention_forward(self, x, context=None, mask=None, **kwargs):
     k_in = self.to_k(context_k)
     v_in = self.to_v(context_v)
 
-    q, k, v = (rearrange(t, 'b n (h d) -> b n h d', h=h) for t in (q_in, k_in, v_in))
+    q, k, v = (t.reshape(t.shape[0], t.shape[1], h, -1) for t in (q_in, k_in, v_in))
+
     del q_in, k_in, v_in
 
     dtype = q.dtype
@@ -497,7 +498,8 @@ def xformers_attention_forward(self, x, context=None, mask=None, **kwargs):
 
     out = out.to(dtype)
 
-    out = rearrange(out, 'b n h d -> b n (h d)', h=h)
+    b, n, h, d = out.shape
+    out = out.reshape(b, n, h * d)
     return self.to_out(out)
 
 

modules/sd_hijack_unet.py

@@ -1,5 +1,7 @@
 import torch
 from packaging import version
+from einops import repeat
+import math
 
 from modules import devices
 from modules.sd_hijack_utils import CondFunc
@@ -36,7 +38,7 @@ th = TorchHijackForUnet()
 
 # Below are monkey patches to enable upcasting a float16 UNet for float32 sampling
 def apply_model(orig_func, self, x_noisy, t, cond, **kwargs):
-
+    """Always make sure inputs to unet are in correct dtype."""
     if isinstance(cond, dict):
         for y in cond.keys():
             if isinstance(cond[y], list):
@@ -45,7 +47,59 @@ def apply_model(orig_func, self, x_noisy, t, cond, **kwargs):
                 cond[y] = cond[y].to(devices.dtype_unet) if isinstance(cond[y], torch.Tensor) else cond[y]
 
     with devices.autocast():
-        return orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs).float()
+        result = orig_func(self, x_noisy.to(devices.dtype_unet), t.to(devices.dtype_unet), cond, **kwargs)
+        if devices.unet_needs_upcast:
+            return result.float()
+        else:
+            return result
+
+
+# Monkey patch to create timestep embed tensor on device, avoiding a block.
+def timestep_embedding(_, timesteps, dim, max_period=10000, repeat_only=False):
+    """
+    Create sinusoidal timestep embeddings.
+    :param timesteps: a 1-D Tensor of N indices, one per batch element.
+                      These may be fractional.
+    :param dim: the dimension of the output.
+    :param max_period: controls the minimum frequency of the embeddings.
+    :return: an [N x dim] Tensor of positional embeddings.
+    """
+    if not repeat_only:
+        half = dim // 2
+        freqs = torch.exp(
+            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32, device=timesteps.device) / half
+        )
+        args = timesteps[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+    else:
+        embedding = repeat(timesteps, 'b -> b d', d=dim)
+    return embedding
+
+
+# Monkey patch to SpatialTransformer removing unnecessary contiguous calls.
+# Prevents a lot of unnecessary aten::copy_ calls
+def spatial_transformer_forward(_, self, x: torch.Tensor, context=None):
+    # note: if no context is given, cross-attention defaults to self-attention
+    if not isinstance(context, list):
+        context = [context]
+    b, c, h, w = x.shape
+    x_in = x
+    x = self.norm(x)
+    if not self.use_linear:
+        x = self.proj_in(x)
+    x = x.permute(0, 2, 3, 1).reshape(b, h * w, c)
+    if self.use_linear:
+        x = self.proj_in(x)
+    for i, block in enumerate(self.transformer_blocks):
+        x = block(x, context=context[i])
+    if self.use_linear:
+        x = self.proj_out(x)
+    x = x.view(b, h, w, c).permute(0, 3, 1, 2)
+    if not self.use_linear:
+        x = self.proj_out(x)
+    return x + x_in
 
 
 class GELUHijack(torch.nn.GELU, torch.nn.Module):
@@ -64,12 +118,15 @@ def hijack_ddpm_edit():
     if not ddpm_edit_hijack:
         CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.decode_first_stage', first_stage_sub, first_stage_cond)
         CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.encode_first_stage', first_stage_sub, first_stage_cond)
-        ddpm_edit_hijack = CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.apply_model', apply_model, unet_needs_upcast)
+        ddpm_edit_hijack = CondFunc('modules.models.diffusion.ddpm_edit.LatentDiffusion.apply_model', apply_model)
 
 
 unet_needs_upcast = lambda *args, **kwargs: devices.unet_needs_upcast
 CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.apply_model', apply_model, unet_needs_upcast)
+CondFunc('ldm.modules.diffusionmodules.openaimodel.timestep_embedding', timestep_embedding)
+CondFunc('ldm.modules.attention.SpatialTransformer.forward', spatial_transformer_forward)
 CondFunc('ldm.modules.diffusionmodules.openaimodel.timestep_embedding', lambda orig_func, timesteps, *args, **kwargs: orig_func(timesteps, *args, **kwargs).to(torch.float32 if timesteps.dtype == torch.int64 else devices.dtype_unet), unet_needs_upcast)
+
 if version.parse(torch.__version__) <= version.parse("1.13.2") or torch.cuda.is_available():
     CondFunc('ldm.modules.diffusionmodules.util.GroupNorm32.forward', lambda orig_func, self, *args, **kwargs: orig_func(self.float(), *args, **kwargs), unet_needs_upcast)
     CondFunc('ldm.modules.attention.GEGLU.forward', lambda orig_func, self, x: orig_func(self.float(), x.float()).to(devices.dtype_unet), unet_needs_upcast)
@@ -81,5 +138,17 @@ CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.decode_first_stage', first_s
 CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.encode_first_stage', first_stage_sub, first_stage_cond)
 CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.get_first_stage_encoding', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).float(), first_stage_cond)
 
-CondFunc('sgm.modules.diffusionmodules.wrappers.OpenAIWrapper.forward', apply_model, unet_needs_upcast)
+CondFunc('ldm.models.diffusion.ddpm.LatentDiffusion.apply_model', apply_model)
-CondFunc('sgm.modules.diffusionmodules.openaimodel.timestep_embedding', lambda orig_func, timesteps, *args, **kwargs: orig_func(timesteps, *args, **kwargs).to(torch.float32 if timesteps.dtype == torch.int64 else devices.dtype_unet), unet_needs_upcast)
+CondFunc('sgm.modules.diffusionmodules.wrappers.OpenAIWrapper.forward', apply_model)
+
+
+def timestep_embedding_cast_result(orig_func, timesteps, *args, **kwargs):
+    if devices.unet_needs_upcast and timesteps.dtype == torch.int64:
+        dtype = torch.float32
+    else:
+        dtype = devices.dtype_unet
+    return orig_func(timesteps, *args, **kwargs).to(dtype=dtype)
+
+
+CondFunc('ldm.modules.diffusionmodules.openaimodel.timestep_embedding', timestep_embedding_cast_result)
+CondFunc('sgm.modules.diffusionmodules.openaimodel.timestep_embedding', timestep_embedding_cast_result)

modules/sd_hijack_utils.py

@@ -1,7 +1,11 @@
 import importlib
 
+
+always_true_func = lambda *args, **kwargs: True
+
+
 class CondFunc:
-    def __new__(cls, orig_func, sub_func, cond_func):
+    def __new__(cls, orig_func, sub_func, cond_func=always_true_func):
         self = super(CondFunc, cls).__new__(cls)
         if isinstance(orig_func, str):
             func_path = orig_func.split('.')
@@ -20,13 +24,13 @@ class CondFunc:
                 print(f"Warning: Failed to resolve {orig_func} for CondFunc hijack")
                 pass
         self.__init__(orig_func, sub_func, cond_func)
-        return lambda *args, **kwargs: self(*args, **kwargs)
+        return lambda *args, **kwargs: self(*args, **kwargs)
-    def __init__(self, orig_func, sub_func, cond_func):
+    def __init__(self, orig_func, sub_func, cond_func):
-        self.__orig_func = orig_func
+        self.__orig_func = orig_func
-        self.__sub_func = sub_func
+        self.__sub_func = sub_func
-        self.__cond_func = cond_func
+        self.__cond_func = cond_func
-    def __call__(self, *args, **kwargs):
+    def __call__(self, *args, **kwargs):
-        if not self.__cond_func or self.__cond_func(self.__orig_func, *args, **kwargs):
+        if not self.__cond_func or self.__cond_func(self.__orig_func, *args, **kwargs):
-            return self.__sub_func(self.__orig_func, *args, **kwargs)
+            return self.__sub_func(self.__orig_func, *args, **kwargs)
-        else:
+        else:
-            return self.__orig_func(*args, **kwargs)
+            return self.__orig_func(*args, **kwargs)

modules/sd_models.py

@@ -380,6 +380,13 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
     model.is_sd2 = not model.is_sdxl and hasattr(model.cond_stage_model, 'model')
     model.is_sd1 = not model.is_sdxl and not model.is_sd2
     model.is_ssd = model.is_sdxl and 'model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight' not in state_dict.keys()
+    # Set is_sdxl_inpaint flag.
+    diffusion_model_input = state_dict.get('diffusion_model.input_blocks.0.0.weight', None)
+    model.is_sdxl_inpaint = (
+        model.is_sdxl and
+        diffusion_model_input is not None and
+        diffusion_model_input.shape[1] == 9
+    )
     if model.is_sdxl:
         sd_models_xl.extend_sdxl(model)
 
@@ -403,6 +410,7 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
         model.float()
         model.alphas_cumprod_original = model.alphas_cumprod
         devices.dtype_unet = torch.float32
+        assert shared.cmd_opts.precision != "half", "Cannot use --precision half with --no-half"
         timer.record("apply float()")
     else:
         vae = model.first_stage_model
@@ -540,7 +548,7 @@ def repair_config(sd_config):
     if hasattr(sd_config.model.params, 'unet_config'):
         if shared.cmd_opts.no_half:
             sd_config.model.params.unet_config.params.use_fp16 = False
-        elif shared.cmd_opts.upcast_sampling:
+        elif shared.cmd_opts.upcast_sampling or shared.cmd_opts.precision == "half":
             sd_config.model.params.unet_config.params.use_fp16 = True
 
     if getattr(sd_config.model.params.first_stage_config.params.ddconfig, "attn_type", None) == "vanilla-xformers" and not shared.xformers_available:
@@ -551,6 +559,14 @@ def repair_config(sd_config):
         karlo_path = os.path.join(paths.models_path, 'karlo')
         sd_config.model.params.noise_aug_config.params.clip_stats_path = sd_config.model.params.noise_aug_config.params.clip_stats_path.replace("checkpoints/karlo_models", karlo_path)
 
+    # Do not use checkpoint for inference.
+    # This helps prevent extra performance overhead on checking parameters.
+    # The perf overhead is about 100ms/it on 4090 for SDXL.
+    if hasattr(sd_config.model.params, "network_config"):
+        sd_config.model.params.network_config.params.use_checkpoint = False
+    if hasattr(sd_config.model.params, "unet_config"):
+        sd_config.model.params.unet_config.params.use_checkpoint = False
+
 
 def rescale_zero_terminal_snr_abar(alphas_cumprod):
     alphas_bar_sqrt = alphas_cumprod.sqrt()
@@ -659,10 +675,11 @@ def get_empty_cond(sd_model):
 
 
 def send_model_to_cpu(m):
-    if m.lowvram:
+    if m is not None:
-        lowvram.send_everything_to_cpu()
+        if m.lowvram:
-    else:
+            lowvram.send_everything_to_cpu()
-        m.to(devices.cpu)
+        else:
+            m.to(devices.cpu)
 
     devices.torch_gc()
 

modules/sd_models_config.py

@@ -35,7 +35,7 @@ def is_using_v_parameterization_for_sd2(state_dict):
 
     with sd_disable_initialization.DisableInitialization():
         unet = ldm.modules.diffusionmodules.openaimodel.UNetModel(
-            use_checkpoint=True,
+            use_checkpoint=False,
             use_fp16=False,
             image_size=32,
             in_channels=4,

modules/sd_models_xl.py

@@ -35,11 +35,10 @@ def get_learned_conditioning(self: sgm.models.diffusion.DiffusionEngine, batch:
 
 
 def apply_model(self: sgm.models.diffusion.DiffusionEngine, x, t, cond):
-    sd = self.model.state_dict()
+    """WARNING: This function is called once per denoising iteration. DO NOT add
-    diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
+    expensive functionc calls such as `model.state_dict`. """
-    if diffusion_model_input is not None:
+    if self.is_sdxl_inpaint:
-        if diffusion_model_input.shape[1] == 9:
+        x = torch.cat([x] + cond['c_concat'], dim=1)
-            x = torch.cat([x] + cond['c_concat'], dim=1)
 
     return self.model(x, t, cond)
 

modules/sd_samplers.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import functools
-
+import logging
 from modules import sd_samplers_kdiffusion, sd_samplers_timesteps, sd_samplers_lcm, shared, sd_samplers_common, sd_schedulers
 
 # imports for functions that previously were here and are used by other modules
@@ -122,4 +122,11 @@ def get_sampler_and_scheduler(sampler_name, scheduler_name):
     return sampler.name, found_scheduler.label
 
 
+def fix_p_invalid_sampler_and_scheduler(p):
+    i_sampler_name, i_scheduler = p.sampler_name, p.scheduler
+    p.sampler_name, p.scheduler = get_sampler_and_scheduler(p.sampler_name, p.scheduler)
+    if p.sampler_name != i_sampler_name or i_scheduler != p.scheduler:
+        logging.warning(f'Sampler Scheduler autocorrection: "{i_sampler_name}" -> "{p.sampler_name}", "{i_scheduler}" -> "{p.scheduler}"')
+
+
 set_samplers()

modules/sd_samplers_cfg_denoiser.py

@@ -212,9 +212,16 @@ class CFGDenoiser(torch.nn.Module):
         uncond = denoiser_params.text_uncond
         skip_uncond = False
 
-        # alternating uncond allows for higher thresholds without the quality loss normally expected from raising it
+        if shared.opts.skip_early_cond != 0. and self.step / self.total_steps <= shared.opts.skip_early_cond:
-        if self.step % 2 and s_min_uncond > 0 and sigma[0] < s_min_uncond and not is_edit_model:
             skip_uncond = True
+            self.p.extra_generation_params["Skip Early CFG"] = shared.opts.skip_early_cond
+        elif (self.step % 2 or shared.opts.s_min_uncond_all) and s_min_uncond > 0 and sigma[0] < s_min_uncond and not is_edit_model:
+            skip_uncond = True
+            self.p.extra_generation_params["NGMS"] = s_min_uncond
+            if shared.opts.s_min_uncond_all:
+                self.p.extra_generation_params["NGMS all steps"] = shared.opts.s_min_uncond_all
+
+        if skip_uncond:
             x_in = x_in[:-batch_size]
             sigma_in = sigma_in[:-batch_size]
 

modules/sd_samplers_timesteps_impl.py

@@ -5,13 +5,14 @@ import numpy as np
 
 from modules import shared
 from modules.models.diffusion.uni_pc import uni_pc
+from modules.torch_utils import float64
 
 
 @torch.no_grad()
 def ddim(model, x, timesteps, extra_args=None, callback=None, disable=None, eta=0.0):
     alphas_cumprod = model.inner_model.inner_model.alphas_cumprod
     alphas = alphas_cumprod[timesteps]
-    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' and x.device.type != 'xpu' else torch.float32)
+    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(float64(x))
     sqrt_one_minus_alphas = torch.sqrt(1 - alphas)
     sigmas = eta * np.sqrt((1 - alphas_prev.cpu().numpy()) / (1 - alphas.cpu()) * (1 - alphas.cpu() / alphas_prev.cpu().numpy()))
 
@@ -43,7 +44,7 @@ def ddim(model, x, timesteps, extra_args=None, callback=None, disable=None, eta=
 def plms(model, x, timesteps, extra_args=None, callback=None, disable=None):
     alphas_cumprod = model.inner_model.inner_model.alphas_cumprod
     alphas = alphas_cumprod[timesteps]
-    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(torch.float64 if x.device.type != 'mps' and x.device.type != 'xpu' else torch.float32)
+    alphas_prev = alphas_cumprod[torch.nn.functional.pad(timesteps[:-1], pad=(1, 0))].to(float64(x))
     sqrt_one_minus_alphas = torch.sqrt(1 - alphas)
 
     extra_args = {} if extra_args is None else extra_args

modules/sd_schedulers.py

@@ -4,6 +4,9 @@ import torch
 
 import k_diffusion
 
+import numpy as np
+
+from modules import shared
 
 @dataclasses.dataclass
 class Scheduler:
@@ -30,6 +33,41 @@ def sgm_uniform(n, sigma_min, sigma_max, inner_model, device):
     sigs += [0.0]
     return torch.FloatTensor(sigs).to(device)
 
+def get_align_your_steps_sigmas(n, sigma_min, sigma_max, device='cpu'):
+    # https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html
+    def loglinear_interp(t_steps, num_steps):
+        """
+        Performs log-linear interpolation of a given array of decreasing numbers.
+        """
+        xs = np.linspace(0, 1, len(t_steps))
+        ys = np.log(t_steps[::-1])
+
+        new_xs = np.linspace(0, 1, num_steps)
+        new_ys = np.interp(new_xs, xs, ys)
+
+        interped_ys = np.exp(new_ys)[::-1].copy()
+        return interped_ys
+
+    if shared.sd_model.is_sdxl:
+        sigmas = [14.615, 6.315, 3.771, 2.181, 1.342, 0.862, 0.555, 0.380, 0.234, 0.113, 0.029]
+    else:
+        # Default to SD 1.5 sigmas.
+        sigmas = [14.615, 6.475, 3.861, 2.697, 1.886, 1.396, 0.963, 0.652, 0.399, 0.152, 0.029]
+
+    if n != len(sigmas):
+        sigmas = np.append(loglinear_interp(sigmas, n), [0.0])
+    else:
+        sigmas.append(0.0)
+
+    return torch.FloatTensor(sigmas).to(device)
+
+def kl_optimal(n, sigma_min, sigma_max, device):
+    alpha_min = torch.arctan(torch.tensor(sigma_min, device=device))
+    alpha_max = torch.arctan(torch.tensor(sigma_max, device=device))
+    step_indices = torch.arange(n + 1, device=device)
+    sigmas = torch.tan(step_indices / n * alpha_min + (1.0 - step_indices / n) * alpha_max)
+    return sigmas
+
 
 schedulers = [
     Scheduler('automatic', 'Automatic', None),
@@ -38,6 +76,8 @@ schedulers = [
     Scheduler('exponential', 'Exponential', k_diffusion.sampling.get_sigmas_exponential),
     Scheduler('polyexponential', 'Polyexponential', k_diffusion.sampling.get_sigmas_polyexponential, default_rho=1.0),
     Scheduler('sgm_uniform', 'SGM Uniform', sgm_uniform, need_inner_model=True, aliases=["SGMUniform"]),
+    Scheduler('kl_optimal', 'KL Optimal', kl_optimal),
+    Scheduler('align_your_steps', 'Align Your Steps', get_align_your_steps_sigmas),
 ]
 
 schedulers_map = {**{x.name: x for x in schedulers}, **{x.label: x for x in schedulers}}

modules/shared_init.py

@@ -31,6 +31,14 @@ def initialize():
     devices.dtype_vae = torch.float32 if cmd_opts.no_half or cmd_opts.no_half_vae else torch.float16
     devices.dtype_inference = torch.float32 if cmd_opts.precision == 'full' else devices.dtype
 
+    if cmd_opts.precision == "half":
+        msg = "--no-half and --no-half-vae conflict with --precision half"
+        assert devices.dtype == torch.float16, msg
+        assert devices.dtype_vae == torch.float16, msg
+        assert devices.dtype_inference == torch.float16, msg
+        devices.force_fp16 = True
+        devices.force_model_fp16()
+
     shared.device = devices.device
     shared.weight_load_location = None if cmd_opts.lowram else "cpu"
 

modules/shared_options.py

@@ -209,7 +209,8 @@ options_templates.update(options_section(('img2img', "img2img", "sd"), {
 
 options_templates.update(options_section(('optimizations', "Optimizations", "sd"), {
     "cross_attention_optimization": OptionInfo("Automatic", "Cross attention optimization", gr.Dropdown, lambda: {"choices": shared_items.cross_attention_optimizations()}),
-    "s_min_uncond": OptionInfo(0.0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 15.0, "step": 0.01}).link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"),
+    "s_min_uncond": OptionInfo(0.0, "Negative Guidance minimum sigma", gr.Slider, {"minimum": 0.0, "maximum": 15.0, "step": 0.01}, infotext='NGMS').link("PR", "https://github.com/AUTOMATIC1111/stablediffusion-webui/pull/9177").info("skip negative prompt for some steps when the image is almost ready; 0=disable, higher=faster"),
+    "s_min_uncond_all": OptionInfo(False, "Negative Guidance minimum sigma all steps", infotext='NGMS all steps').info("By default, NGMS above skips every other step; this makes it skip all steps"),
     "token_merging_ratio": OptionInfo(0.0, "Token merging ratio", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio').link("PR", "https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9256").info("0=disable, higher=faster"),
     "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"),
     "token_merging_ratio_hr": OptionInfo(0.0, "Token merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio hr').info("only applies if non-zero and overrides above"),
@@ -380,7 +381,8 @@ options_templates.update(options_section(('sampler-params', "Sampler parameters"
     'uni_pc_skip_type': OptionInfo("time_uniform", "UniPC skip type", gr.Radio, {"choices": ["time_uniform", "time_quadratic", "logSNR"]}, infotext='UniPC skip type'),
     'uni_pc_order': OptionInfo(3, "UniPC order", gr.Slider, {"minimum": 1, "maximum": 50, "step": 1}, infotext='UniPC order').info("must be < sampling steps"),
     'uni_pc_lower_order_final': OptionInfo(True, "UniPC lower order final", infotext='UniPC lower order final'),
-    'sd_noise_schedule': OptionInfo("Default", "Noise schedule for sampling", gr.Radio, {"choices": ["Default", "Zero Terminal SNR"]}, infotext="Noise Schedule").info("for use with zero terminal SNR trained models")
+    'sd_noise_schedule': OptionInfo("Default", "Noise schedule for sampling", gr.Radio, {"choices": ["Default", "Zero Terminal SNR"]}, infotext="Noise Schedule").info("for use with zero terminal SNR trained models"),
+    'skip_early_cond': OptionInfo(0.0, "Ignore negative prompt during early sampling", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}, infotext="Skip Early CFG").info("disables CFG on a proportion of steps at the beginning of generation; 0=skip none; 1=skip all; can both improve sample diversity/quality and speed up sampling"),
 }))
 
 options_templates.update(options_section(('postprocessing', "Postprocessing", "postprocessing"), {

modules/torch_utils.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import torch.nn
+import torch
 
 
 def get_param(model) -> torch.nn.Parameter:
@@ -15,3 +16,11 @@ def get_param(model) -> torch.nn.Parameter:
         return param
 
     raise ValueError(f"No parameters found in model {model!r}")
+
+
+def float64(t: torch.Tensor):
+    """return torch.float64 if device is not mps or xpu, else return torch.float32"""
+    match t.device.type:
+        case 'mps', 'xpu':
+            return torch.float32
+    return torch.float64

modules/ui.py

@@ -566,18 +566,25 @@ def create_ui():
                                 init_mask_inpaint = gr.Image(label="Mask", source="upload", interactive=True, type="pil", image_mode="RGBA", elem_id="img_inpaint_mask")
 
                             with gr.TabItem('Batch', id='batch', elem_id="img2img_batch_tab") as tab_batch:
-                                hidden = '<br>Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else ''
+                                with gr.Tabs(elem_id="img2img_batch_source"):
-                                gr.HTML(
+                                    img2img_batch_source_type = gr.Textbox(visible=False, value="upload")
-                                    "<p style='padding-bottom: 1em;' class=\"text-gray-500\">Process images in a directory on the same machine where the server is running." +
+                                    with gr.TabItem('Upload', id='batch_upload', elem_id="img2img_batch_upload_tab") as tab_batch_upload:
-                                    "<br>Use an empty output directory to save pictures normally instead of writing to the output directory." +
+                                        img2img_batch_upload = gr.Files(label="Files", interactive=True, elem_id="img2img_batch_upload")
-                                    f"<br>Add inpaint batch mask directory to enable inpaint batch processing."
+                                    with gr.TabItem('From directory', id='batch_from_dir', elem_id="img2img_batch_from_dir_tab") as tab_batch_from_dir:
-                                    f"{hidden}</p>"
+                                        hidden = '<br>Disabled when launched with --hide-ui-dir-config.' if shared.cmd_opts.hide_ui_dir_config else ''
-                                )
+                                        gr.HTML(
-                                img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, elem_id="img2img_batch_input_dir")
+                                            "<p style='padding-bottom: 1em;' class=\"text-gray-500\">Process images in a directory on the same machine where the server is running." +
-                                img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, elem_id="img2img_batch_output_dir")
+                                            "<br>Use an empty output directory to save pictures normally instead of writing to the output directory." +
-                                img2img_batch_inpaint_mask_dir = gr.Textbox(label="Inpaint batch mask directory (required for inpaint batch processing only)", **shared.hide_dirs, elem_id="img2img_batch_inpaint_mask_dir")
+                                            f"<br>Add inpaint batch mask directory to enable inpaint batch processing."
+                                            f"{hidden}</p>"
+                                        )
+                                        img2img_batch_input_dir = gr.Textbox(label="Input directory", **shared.hide_dirs, elem_id="img2img_batch_input_dir")
+                                        img2img_batch_output_dir = gr.Textbox(label="Output directory", **shared.hide_dirs, elem_id="img2img_batch_output_dir")
+                                        img2img_batch_inpaint_mask_dir = gr.Textbox(label="Inpaint batch mask directory (required for inpaint batch processing only)", **shared.hide_dirs, elem_id="img2img_batch_inpaint_mask_dir")
+                                tab_batch_upload.select(fn=lambda: "upload", inputs=[], outputs=[img2img_batch_source_type])
+                                tab_batch_from_dir.select(fn=lambda: "from dir", inputs=[], outputs=[img2img_batch_source_type])
                                 with gr.Accordion("PNG info", open=False):
-                                    img2img_batch_use_png_info = gr.Checkbox(label="Append png info to prompts", **shared.hide_dirs, elem_id="img2img_batch_use_png_info")
+                                    img2img_batch_use_png_info = gr.Checkbox(label="Append png info to prompts", elem_id="img2img_batch_use_png_info")
                                     img2img_batch_png_info_dir = gr.Textbox(label="PNG info directory", **shared.hide_dirs, placeholder="Leave empty to use input directory", elem_id="img2img_batch_png_info_dir")
                                     img2img_batch_png_info_props = gr.CheckboxGroup(["Prompt", "Negative prompt", "Seed", "CFG scale", "Sampler", "Steps", "Model hash"], label="Parameters to take from png info", info="Prompts from png info will be appended to prompts set in ui.")
 
@@ -759,6 +766,8 @@ def create_ui():
                     img2img_batch_use_png_info,
                     img2img_batch_png_info_props,
                     img2img_batch_png_info_dir,
+                    img2img_batch_source_type,
+                    img2img_batch_upload,
                 ] + custom_inputs,
                 outputs=[
                     output_panel.gallery,

requirements_versions.txt

@@ -1,3 +1,4 @@
+setuptools==69.5.1  # temp fix for compatibility with some old packages
 GitPython==3.1.32
 Pillow==9.5.0
 accelerate==0.21.0

scripts/xyz_grid.py

@@ -95,15 +95,15 @@ def confirm_checkpoints_or_none(p, xs):
             raise RuntimeError(f"Unknown checkpoint: {x}")
 
 
-def apply_clip_skip(p, x, xs):
+def confirm_range(min_val, max_val, axis_label):
-    opts.data["CLIP_stop_at_last_layers"] = x
+    """Generates a AxisOption.confirm() function that checks all values are within the specified range."""
 
+    def confirm_range_fun(p, xs):
+        for x in xs:
+            if not (max_val >= x >= min_val):
+                raise ValueError(f'{axis_label} value "{x}" out of range [{min_val}, {max_val}]')
 
-def apply_upscale_latent_space(p, x, xs):
+    return confirm_range_fun
-    if x.lower().strip() != '0':
-        opts.data["use_scale_latent_for_hires_fix"] = True
-    else:
-        opts.data["use_scale_latent_for_hires_fix"] = False
 
 
 def apply_size(p, x: str, xs) -> None:
@@ -118,21 +118,16 @@ def apply_size(p, x: str, xs) -> None:
 
 
 def find_vae(name: str):
-    if name.lower() in ['auto', 'automatic']:
+    match name := name.lower().strip():
-        return modules.sd_vae.unspecified
+        case 'auto', 'automatic':
-    if name.lower() == 'none':
+            return 'Automatic'
-        return None
+        case 'none':
-    else:
+            return 'None'
-        choices = [x for x in sorted(modules.sd_vae.vae_dict, key=lambda x: len(x)) if name.lower().strip() in x.lower()]
+    return next((k for k in modules.sd_vae.vae_dict if k.lower() == name), print(f'No VAE found for {name}; using Automatic') or 'Automatic')
-        if len(choices) == 0:
-            print(f"No VAE found for {name}; using automatic")
-            return modules.sd_vae.unspecified
-        else:
-            return modules.sd_vae.vae_dict[choices[0]]
 
 
 def apply_vae(p, x, xs):
-    modules.sd_vae.reload_vae_weights(shared.sd_model, vae_file=find_vae(x))
+    p.override_settings['sd_vae'] = find_vae(x)
 
 
 def apply_styles(p: StableDiffusionProcessingTxt2Img, x: str, _):
@@ -140,7 +135,7 @@ def apply_styles(p: StableDiffusionProcessingTxt2Img, x: str, _):
 
 
 def apply_uni_pc_order(p, x, xs):
-    opts.data["uni_pc_order"] = min(x, p.steps - 1)
+    p.override_settings['uni_pc_order'] = min(x, p.steps - 1)
 
 
 def apply_face_restore(p, opt, x):
@@ -162,12 +157,14 @@ def apply_override(field, boolean: bool = False):
         if boolean:
             x = True if x.lower() == "true" else False
         p.override_settings[field] = x
+
     return fun
 
 
 def boolean_choice(reverse: bool = False):
     def choice():
         return ["False", "True"] if reverse else ["True", "False"]
+
     return choice
 
 
@@ -212,7 +209,7 @@ def list_to_csv_string(data_list):
 
 
 def csv_string_to_list_strip(data_str):
-    return list(map(str.strip, chain.from_iterable(csv.reader(StringIO(data_str)))))
+    return list(map(str.strip, chain.from_iterable(csv.reader(StringIO(data_str), skipinitialspace=True))))
 
 
 class AxisOption:
@@ -264,13 +261,13 @@ axis_options = [
     AxisOption("Schedule max sigma", float, apply_override("sigma_max")),
     AxisOption("Schedule rho", float, apply_override("rho")),
     AxisOption("Eta", float, apply_field("eta")),
-    AxisOption("Clip skip", int, apply_clip_skip),
+    AxisOption("Clip skip", int, apply_override('CLIP_stop_at_last_layers')),
     AxisOption("Denoising", float, apply_field("denoising_strength")),
     AxisOption("Initial noise multiplier", float, apply_field("initial_noise_multiplier")),
     AxisOption("Extra noise", float, apply_override("img2img_extra_noise")),
     AxisOptionTxt2Img("Hires upscaler", str, apply_field("hr_upscaler"), choices=lambda: [*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]]),
     AxisOptionImg2Img("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight")),
-    AxisOption("VAE", str, apply_vae, cost=0.7, choices=lambda: ['None'] + list(sd_vae.vae_dict)),
+    AxisOption("VAE", str, apply_vae, cost=0.7, choices=lambda: ['Automatic', 'None'] + list(sd_vae.vae_dict)),
     AxisOption("Styles", str, apply_styles, choices=lambda: list(shared.prompt_styles.styles)),
     AxisOption("UniPC Order", int, apply_uni_pc_order, cost=0.5),
     AxisOption("Face restore", str, apply_face_restore, format_value=format_value),
@@ -399,18 +396,12 @@ def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend
 
 class SharedSettingsStackHelper(object):
     def __enter__(self):
-        self.CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers
+        pass
-        self.vae = opts.sd_vae
-        self.uni_pc_order = opts.uni_pc_order
 
     def __exit__(self, exc_type, exc_value, tb):
-        opts.data["sd_vae"] = self.vae
-        opts.data["uni_pc_order"] = self.uni_pc_order
         modules.sd_models.reload_model_weights()
         modules.sd_vae.reload_vae_weights()
 
-        opts.data["CLIP_stop_at_last_layers"] = self.CLIP_stop_at_last_layers
-
 
 re_range = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\(([+-]\d+)\s*\))?\s*")
 re_range_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\(([+-]\d+(?:.\d*)?)\s*\))?\s*")
@@ -572,7 +563,7 @@ class Script(scripts.Script):
                     mc = re_range_count.fullmatch(val)
                     if m is not None:
                         start = int(m.group(1))
-                        end = int(m.group(2))+1
+                        end = int(m.group(2)) + 1
                         step = int(m.group(3)) if m.group(3) is not None else 1
 
                         valslist_ext += list(range(start, end, step))
@@ -725,11 +716,11 @@ class Script(scripts.Script):
             ydim = len(ys) if vary_seeds_y else 1
 
             if vary_seeds_x:
-               pc.seed += ix
+                pc.seed += ix
             if vary_seeds_y:
-               pc.seed += iy * xdim
+                pc.seed += iy * xdim
             if vary_seeds_z:
-               pc.seed += iz * xdim * ydim
+                pc.seed += iz * xdim * ydim
 
             try:
                 res = process_images(pc)
@@ -797,18 +788,18 @@ class Script(scripts.Script):
         z_count = len(zs)
 
         # Set the grid infotexts to the real ones with extra_generation_params (1 main grid + z_count sub-grids)
-        processed.infotexts[:1+z_count] = grid_infotext[:1+z_count]
+        processed.infotexts[:1 + z_count] = grid_infotext[:1 + z_count]
 
         if not include_lone_images:
             # Don't need sub-images anymore, drop from list:
-            processed.images = processed.images[:z_count+1]
+            processed.images = processed.images[:z_count + 1]
 
         if opts.grid_save:
             # Auto-save main and sub-grids:
             grid_count = z_count + 1 if z_count > 1 else 1
             for g in range(grid_count):
                 # TODO: See previous comment about intentional data misalignment.
-                adj_g = g-1 if g > 0 else g
+                adj_g = g - 1 if g > 0 else g
                 images.save_image(processed.images[g], p.outpath_grids, "xyz_grid", info=processed.infotexts[g], extension=opts.grid_format, prompt=processed.all_prompts[adj_g], seed=processed.all_seeds[adj_g], grid=True, p=processed)
                 if not include_sub_grids:  # if not include_sub_grids then skip saving after the first grid
                     break

style.css

@@ -807,6 +807,8 @@ table.popup-table .link{
 
 #tab_extensions table{
     border-collapse: collapse;
+    overflow-x: auto;
+    display: block;
 }
 
 #tab_extensions table td, #tab_extensions table th{

webui-macos-env.sh

@@ -11,7 +11,12 @@ fi
 
 export install_dir="$HOME"
 export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate"
-export TORCH_COMMAND="pip install torch==2.1.2 torchvision==0.16.2"
 export PYTORCH_ENABLE_MPS_FALLBACK=1
 
+if [[ "$(sysctl -n machdep.cpu.brand_string)" =~ ^.*"Intel".*$ ]]; then
+    export TORCH_COMMAND="pip install torch==2.1.2 torchvision==0.16.2"
+else
+    export TORCH_COMMAND="pip install torch==2.3.0 torchvision==0.18.0"
+fi
+
 ####################################################################