more changes for #13865: fix formatting, rename the function, add comment and add a readme entry

README.md

@@ -91,6 +91,7 @@ A browser interface based on Gradio library for Stable Diffusion.
 - Eased resolution restriction: generated image's dimensions must be a multiple of 8 rather than 64
 - Now with a license!
 - Reorder elements in the UI from settings screen
+- [Segmind Stable Diffusion](https://huggingface.co/segmind/SSD-1B) support
 
 ## Installation and Running
 Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for:

modules/sd_hijack.py

@@ -184,7 +184,9 @@ class StableDiffusionModelHijack:
             errors.display(e, "applying cross attention optimization")
             undo_optimizations()
 
-    def conv_ssd(self, m):
+    def convert_sdxl_to_ssd(self, m):
+        """Converts an SDXL model to a Segmind Stable Diffusion model (see https://huggingface.co/segmind/SSD-1B)"""
+
         delattr(m.model.diffusion_model.middle_block, '1')
         delattr(m.model.diffusion_model.middle_block, '2')
         for i in ['9', '8', '7', '6', '5', '4']:

modules/sd_models.py

@@ -357,7 +357,7 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
         sd_models_xl.extend_sdxl(model)
 
     if model.is_ssd:
-        sd_hijack.model_hijack.conv_ssd(model)
+        sd_hijack.model_hijack.convert_sdxl_to_ssd(model)
 
     if shared.opts.sd_checkpoint_cache > 0:
         # cache newly loaded model