hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-04 11:12:35 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Added support for RunwayML inpainting model

Browse Source
This commit is contained in:
random_thoughtss
2022-10-19 13:47:45 -07:00
parent 604620a7f0
commit 8e7097d06a
4 changed files with 293 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
modules/sd_samplers.py
View File

@@ -136,9 +136,15 @@ class VanillaStableDiffusionSampler:
if self.stop_at is not None and self.step > self.stop_at:
raise InterruptedException
# Have to unwrap the inpainting conditioning here to perform pre-preocessing
image_conditioning = None
if isinstance(cond, dict):
image_conditioning = cond["c_concat"][0]
cond = cond["c_crossattn"][0]
unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)
unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)
assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers'
cond = tensor
@@ -157,6 +163,10 @@ class VanillaStableDiffusionSampler:
img_orig = self.sampler.model.q_sample(self.init_latent, ts)
x_dec = img_orig * self.mask + self.nmask * x_dec
if image_conditioning is not None:
cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
if self.mask is not None:
@@ -182,7 +192,7 @@ class VanillaStableDiffusionSampler:
self.mask = p.mask if hasattr(p, 'mask') else None
self.nmask = p.nmask if hasattr(p, 'nmask') else None
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None):
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = setup_img2img_steps(p, steps)
self.initialize(p)
@@ -202,7 +212,7 @@ class VanillaStableDiffusionSampler:
return samples
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None):
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
self.initialize(p)
self.init_latent = None
@@ -210,6 +220,11 @@ class VanillaStableDiffusionSampler:
steps = steps or p.steps
# Wrap the conditioning models with additional image conditioning for inpainting model
if image_conditioning is not None:
conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
# existing code fails with certain step counts, like 9
try:
samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
@@ -228,7 +243,7 @@ class CFGDenoiser(torch.nn.Module):
self.init_latent = None
self.step = 0
def forward(self, x, sigma, uncond, cond, cond_scale):
def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
if state.interrupted or state.skipped:
raise InterruptedException
@@ -239,28 +254,29 @@ class CFGDenoiser(torch.nn.Module):
repeats = [len(conds_list[i]) for i in range(batch_size)]
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
if tensor.shape[1] == uncond.shape[1]:
cond_in = torch.cat([tensor, uncond])
if shared.batch_cond_uncond:
x_out = self.inner_model(x_in, sigma_in, cond=cond_in)
x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
else:
x_out = torch.zeros_like(x_in)
for batch_offset in range(0, x_out.shape[0], batch_size):
a = batch_offset
b = a + batch_size
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b])
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
else:
x_out = torch.zeros_like(x_in)
batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
for batch_offset in range(0, tensor.shape[0], batch_size):
a = batch_offset
b = min(a + batch_size, tensor.shape[0])
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=tensor[a:b])
x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [tensor[a:b]], "c_concat": [image_cond_in[a:b]]})
x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=uncond)
x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
denoised_uncond = x_out[-uncond.shape[0]:]
denoised = torch.clone(denoised_uncond)
@@ -361,7 +377,7 @@ class KDiffusionSampler:
return extra_params_kwargs
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None):
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = setup_img2img_steps(p, steps)
if p.sampler_noise_scheduler_override:
@@ -389,11 +405,16 @@ class KDiffusionSampler:
self.model_wrap_cfg.init_latent = x
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, xi, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs))
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale
}, disable=False, callback=self.callback_state, **extra_params_kwargs))
return samples
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None):
def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
steps = steps or p.steps
if p.sampler_noise_scheduler_override:
@@ -414,7 +435,12 @@ class KDiffusionSampler:
else:
extra_params_kwargs['sigmas'] = sigmas
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs))
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
'cond': conditioning,
'image_cond': image_conditioning,
'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale
}, disable=False, callback=self.callback_state, **extra_params_kwargs))
return samples