OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-12-29 19:05:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add randomness and denoising strength support to alternative img2img

Browse Source
This commit is contained in:
Elias Sundqvist 2022-09-16 06:40:43 +00:00 committed by AUTOMATIC1111
parent b8cf2ea8ea
commit 2aec11d263
1 changed files with 30 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
scripts/img2imgalt.py
View File

@ -76,10 +76,10 @@ class Script(scripts.Script):
original_prompt = gr.Textbox(label="Original prompt", lines=1)
cfg = gr.Slider(label="Decode CFG scale", minimum=0.0, maximum=15.0, step=0.1, value=1.0)
st = gr.Slider(label="Decode steps", minimum=1, maximum=150, step=1, value=50)
randomness = gr.Slider(label="randomness", minimum=0.0, maximum=1.0, step=0.01, value=0.0)
return [original_prompt, cfg, st, randomness]
return [original_prompt, cfg, st]
def run(self, p, original_prompt, cfg, st):
def run(self, p, original_prompt, cfg, st, randomness):
p.batch_size = 1
p.batch_count = 1
@ -90,18 +90,40 @@ class Script(scripts.Script):
same_everything = same_params and self.cache.latent.shape == lat.shape and np.abs(self.cache.latent-lat).sum() < 100
if same_everything:
noise = self.cache.noise
rec_noise = self.cache.noise
else:
shared.state.job_count += 1
cond = p.sd_model.get_learned_conditioning(p.batch_size * [original_prompt])
uncond = p.sd_model.get_learned_conditioning(p.batch_size * [""])
noise = find_noise_for_image(p, cond, uncond, cfg, st)
self.cache = Cached(noise, cfg, st, lat, original_prompt)
rec_noise = find_noise_for_image(p, cond, uncond, cfg, st)
self.cache = Cached(rec_noise, cfg, st, lat, original_prompt)
rand_noise = processing.create_random_tensors(p.init_latent.shape[1:], [p.seed + x + 1 for x in range(p.init_latent.shape[0])])
combined_noise = ((1 - randomness) * rec_noise + randomness * rand_noise) / ((randomness**2 + (1-randomness)**2) ** 0.5)
sampler = samplers[p.sampler_index].constructor(p.sd_model)
samples_ddim = sampler.sample(p, noise, conditioning, unconditional_conditioning)
return samples_ddim
sigmas = sampler.model_wrap.get_sigmas(p.steps)
t_enc = int(min(p.denoising_strength, 0.999) * p.steps)
noise_dt = combined_noise - ( p.init_latent / sigmas[0] )
noise_dt = noise_dt * sigmas[p.steps - t_enc - 1]
noise = p.init_latent + noise_dt
sigma_sched = sigmas[p.steps - t_enc - 1:]
sampler.model_wrap_cfg.mask = p.mask
sampler.model_wrap_cfg.nmask = p.nmask
sampler.model_wrap_cfg.init_latent = p.init_latent
if hasattr(K.sampling, 'trange'):
K.sampling.trange = lambda *args, **kwargs: sd_samplers.extended_trange(*args, **kwargs)
p.seed = p.seed + 1
return sampler.func(sampler.model_wrap_cfg, noise, sigma_sched, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=sampler.callback_state)
p.sample = sample_extra