From 8e7097d06a6a261580d34375c9d2a9e4ffc63ffa Mon Sep 17 00:00:00 2001 From: random_thoughtss Date: Wed, 19 Oct 2022 13:47:45 -0700 Subject: Added support for RunwayML inpainting model --- modules/sd_samplers.py | 50 ++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 38 insertions(+), 12 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index b58e810b..9d3cf289 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -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 -- cgit v1.2.3 From dde9f960727bfe151d418e43685a2881cf580a17 Mon Sep 17 00:00:00 2001 From: random_thoughtss Date: Wed, 19 Oct 2022 14:14:24 -0700 Subject: added support for ddim img2img --- modules/sd_samplers.py | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 9d3cf289..d270e4df 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -208,6 +208,12 @@ class VanillaStableDiffusionSampler: self.init_latent = x self.step = 0 + # 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]} + + samples = self.launch_sampling(steps, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning)) return samples -- cgit v1.2.3 From c418467c03db916c3e5312e6ac4a67365e196dbd Mon Sep 17 00:00:00 2001 From: random_thoughtss Date: Wed, 19 Oct 2022 15:09:43 -0700 Subject: Don't compute latent mask if were not using it. Also added support for fixed highres_fix generation. --- modules/processing.py | 72 +++++++++++++++++++++++++++++++------------------- modules/sd_samplers.py | 4 +++ 2 files changed, 49 insertions(+), 27 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/processing.py b/modules/processing.py index a6c308f9..684e5833 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -541,12 +541,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): - self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model) - - if not self.enable_hr: - x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self) - + def create_dummy_mask(self, x): + if self.sampler.conditioning_key in {'hybrid', 'concat'}: # The "masked-image" in this case will just be all zeros since the entire image is masked. image_conditioning = torch.zeros(x.shape[0], 3, self.height, self.width, device=x.device) image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning)) @@ -555,11 +551,23 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0) image_conditioning = image_conditioning.to(x.dtype) - samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=image_conditioning) + else: + # Dummy zero conditioning if we're not using inpainting model. + # Still takes up a bit of memory, but no encoder call. + image_conditioning = torch.zeros(x.shape[0], 5, x.shape[-2], x.shape[-1], dtype=x.dtype, device=x.device) + + return image_conditioning + + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): + self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model) + + if not self.enable_hr: + x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self) + samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.create_dummy_mask(x)) return samples x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self) - samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning) + samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.create_dummy_mask(x)) samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2] @@ -596,7 +604,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() - samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps) + samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=self.create_dummy_mask(samples)) return samples @@ -723,26 +731,36 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): elif self.inpainting_fill == 3: self.init_latent = self.init_latent * self.mask - if self.image_mask is not None: - conditioning_mask = np.array(self.image_mask.convert("L")) - conditioning_mask = conditioning_mask.astype(np.float32) / 255.0 - conditioning_mask = torch.from_numpy(conditioning_mask[None, None]) + conditioning_key = self.sampler.conditioning_key - # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0 - conditioning_mask = torch.round(conditioning_mask) + if conditioning_key in {'hybrid', 'concat'}: + if self.image_mask is not None: + conditioning_mask = np.array(self.image_mask.convert("L")) + conditioning_mask = conditioning_mask.astype(np.float32) / 255.0 + conditioning_mask = torch.from_numpy(conditioning_mask[None, None]) + + # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0 + conditioning_mask = torch.round(conditioning_mask) + else: + conditioning_mask = torch.ones(1, 1, *image.shape[-2:]) + + # Create another latent image, this time with a masked version of the original input. + conditioning_mask = conditioning_mask.to(image.device) + conditioning_image = image * (1.0 - conditioning_mask) + conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image)) + + # Create the concatenated conditioning tensor to be fed to `c_concat` + conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=self.init_latent.shape[-2:]) + conditioning_mask = conditioning_mask.expand(conditioning_image.shape[0], -1, -1, -1) + self.image_conditioning = torch.cat([conditioning_mask, conditioning_image], dim=1) + self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype) else: - conditioning_mask = torch.ones(1, 1, *image.shape[-2:]) - - # Create another latent image, this time with a masked version of the original input. - conditioning_mask = conditioning_mask.to(image.device) - conditioning_image = image * (1.0 - conditioning_mask) - conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image)) - - # Create the concatenated conditioning tensor to be fed to `c_concat` - conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=self.init_latent.shape[-2:]) - conditioning_mask = conditioning_mask.expand(conditioning_image.shape[0], -1, -1, -1) - self.image_conditioning = torch.cat([conditioning_mask, conditioning_image], dim=1) - self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype) + self.image_conditioning = torch.zeros( + self.init_latent.shape[0], 5, self.init_latent.shape[-2], self.init_latent.shape[-1], + dtype=self.init_latent.dtype, + device=self.init_latent.device + ) + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self) diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index d270e4df..c21be26e 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -117,6 +117,8 @@ class VanillaStableDiffusionSampler: self.config = None self.last_latent = None + self.conditioning_key = sd_model.model.conditioning_key + def number_of_needed_noises(self, p): return 0 @@ -328,6 +330,8 @@ class KDiffusionSampler: self.config = None self.last_latent = None + self.conditioning_key = sd_model.model.conditioning_key + def callback_state(self, d): step = d['i'] latent = d["denoised"] -- cgit v1.2.3 From 92a17a7a4a13fceb3c3e25a2e854b2a7dd6eb5df Mon Sep 17 00:00:00 2001 From: random_thoughtss Date: Thu, 20 Oct 2022 09:45:03 -0700 Subject: Made dummy latents smaller. Minor code cleanups --- modules/processing.py | 7 ++++--- modules/sd_samplers.py | 6 ++++-- 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/processing.py b/modules/processing.py index 3caac25e..539cde38 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -557,7 +557,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): else: # Dummy zero conditioning if we're not using inpainting model. # Still takes up a bit of memory, but no encoder call. - image_conditioning = torch.zeros(x.shape[0], 5, x.shape[-2], x.shape[-1], dtype=x.dtype, device=x.device) + # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size. + image_conditioning = torch.zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device) return image_conditioning @@ -759,8 +760,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype) else: self.image_conditioning = torch.zeros( - self.init_latent.shape[0], 5, self.init_latent.shape[-2], self.init_latent.shape[-1], - dtype=self.init_latent.dtype, + self.init_latent.shape[0], 5, 1, 1, + dtype=self.init_latent.dtype, device=self.init_latent.device ) diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index c21be26e..cc682593 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -138,7 +138,7 @@ 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 + # Have to unwrap the inpainting conditioning here to perform pre-processing image_conditioning = None if isinstance(cond, dict): image_conditioning = cond["c_concat"][0] @@ -146,7 +146,7 @@ class VanillaStableDiffusionSampler: 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 @@ -165,6 +165,8 @@ class VanillaStableDiffusionSampler: img_orig = self.sampler.model.q_sample(self.init_latent, ts) x_dec = img_orig * self.mask + self.nmask * x_dec + # Wrap the image conditioning back up since the DDIM code can accept the dict directly. + # Note that they need to be lists because it just concatenates them later. if image_conditioning is not None: cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]} unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]} -- cgit v1.2.3 From d23a46ceaa76af2847f11172f32c92665c268b1b Mon Sep 17 00:00:00 2001 From: Vladimir Repin <32306715+mezotaken@users.noreply.github.com> Date: Thu, 20 Oct 2022 23:49:14 +0300 Subject: Different approach to skip/interrupt with highres fix --- modules/processing.py | 4 +++- modules/sd_samplers.py | 4 ++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/processing.py b/modules/processing.py index 6324ca91..bcb0c32c 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -587,7 +587,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x = None devices.torch_gc() - return self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps) or samples + samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps) + + return samples class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index b58e810b..7ff77c01 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -196,6 +196,7 @@ class VanillaStableDiffusionSampler: x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise) self.init_latent = x + self.last_latent = x self.step = 0 samples = self.launch_sampling(steps, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning)) @@ -206,6 +207,7 @@ class VanillaStableDiffusionSampler: self.initialize(p) self.init_latent = None + self.last_latent = x self.step = 0 steps = steps or p.steps @@ -388,6 +390,7 @@ class KDiffusionSampler: extra_params_kwargs['sigmas'] = sigma_sched self.model_wrap_cfg.init_latent = x + self.last_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)) @@ -414,6 +417,7 @@ class KDiffusionSampler: else: extra_params_kwargs['sigmas'] = sigmas + self.last_latent = x 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)) return samples -- cgit v1.2.3 From 4fdb53c1e9962507fc8336dad9a0fabfe6c418c0 Mon Sep 17 00:00:00 2001 From: Unnoen Date: Wed, 19 Oct 2022 21:38:10 +1100 Subject: Generate grid preview for progress image --- modules/sd_samplers.py | 26 +++++++++++++++++++++++++- modules/shared.py | 1 + modules/ui.py | 5 ++++- 3 files changed, 30 insertions(+), 2 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index f58a29b9..74a480e5 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -7,7 +7,7 @@ import inspect import k_diffusion.sampling import ldm.models.diffusion.ddim import ldm.models.diffusion.plms -from modules import prompt_parser, devices, processing +from modules import prompt_parser, devices, processing, images from modules.shared import opts, cmd_opts, state import modules.shared as shared @@ -89,6 +89,30 @@ def sample_to_image(samples): x_sample = x_sample.astype(np.uint8) return Image.fromarray(x_sample) +def samples_to_image_grid(samples): + progress_images = [] + for i in range(len(samples)): + # Decode the samples individually to reduce VRAM usage at the cost of a bit of speed. + x_sample = processing.decode_first_stage(shared.sd_model, samples[i:i+1])[0] + x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0) + x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) + x_sample = x_sample.astype(np.uint8) + progress_images.append(Image.fromarray(x_sample)) + + return images.image_grid(progress_images) + +def samples_to_image_grid_combined(samples): + progress_images = [] + # Decode all samples at once to increase speed at the cost of VRAM usage. + x_samples = processing.decode_first_stage(shared.sd_model, samples) + x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0) + + for x_sample in x_samples: + x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) + x_sample = x_sample.astype(np.uint8) + progress_images.append(Image.fromarray(x_sample)) + + return images.image_grid(progress_images) def store_latent(decoded): state.current_latent = decoded diff --git a/modules/shared.py b/modules/shared.py index d9cb65ef..95d6e225 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -294,6 +294,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"), options_templates.update(options_section(('ui', "User interface"), { "show_progressbar": OptionInfo(True, "Show progressbar"), "show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}), + "progress_decode_combined": OptionInfo(False, "Decode all progress images at once. (Slighty speeds up progress generation but consumes significantly more VRAM with large batches.)"), "return_grid": OptionInfo(True, "Show grid in results for web"), "do_not_show_images": OptionInfo(False, "Do not show any images in results for web"), "add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"), diff --git a/modules/ui.py b/modules/ui.py index 56c233ab..de0abc7e 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -318,7 +318,10 @@ def check_progress_call(id_part): if shared.parallel_processing_allowed: if shared.state.sampling_step - shared.state.current_image_sampling_step >= opts.show_progress_every_n_steps and shared.state.current_latent is not None: - shared.state.current_image = modules.sd_samplers.sample_to_image(shared.state.current_latent) + if opts.progress_decode_combined: + shared.state.current_image = modules.sd_samplers.samples_to_image_grid_combined(shared.state.current_latent) + else: + shared.state.current_image = modules.sd_samplers.samples_to_image_grid(shared.state.current_latent) shared.state.current_image_sampling_step = shared.state.sampling_step image = shared.state.current_image -- cgit v1.2.3 From d213d6ca6f90094cb45c11e2f3cb37d25a8d1f94 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Sat, 22 Oct 2022 20:48:13 +0300 Subject: removed the option to use 2x more memory when generating previews added an option to always only show one image in previews removed duplicate code --- modules/sd_samplers.py | 35 ++++++++++------------------------- modules/shared.py | 2 +- modules/ui.py | 6 +++--- 3 files changed, 14 insertions(+), 29 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 74a480e5..0b408a70 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -71,6 +71,7 @@ sampler_extra_params = { 'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'], } + def setup_img2img_steps(p, steps=None): if opts.img2img_fix_steps or steps is not None: steps = int((steps or p.steps) / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0 @@ -82,37 +83,21 @@ def setup_img2img_steps(p, steps=None): return steps, t_enc -def sample_to_image(samples): - x_sample = processing.decode_first_stage(shared.sd_model, samples[0:1])[0] +def single_sample_to_image(sample): + x_sample = processing.decode_first_stage(shared.sd_model, sample.unsqueeze(0))[0] x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0) x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) x_sample = x_sample.astype(np.uint8) return Image.fromarray(x_sample) + +def sample_to_image(samples): + return single_sample_to_image(samples[0]) + + def samples_to_image_grid(samples): - progress_images = [] - for i in range(len(samples)): - # Decode the samples individually to reduce VRAM usage at the cost of a bit of speed. - x_sample = processing.decode_first_stage(shared.sd_model, samples[i:i+1])[0] - x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0) - x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) - x_sample = x_sample.astype(np.uint8) - progress_images.append(Image.fromarray(x_sample)) - - return images.image_grid(progress_images) - -def samples_to_image_grid_combined(samples): - progress_images = [] - # Decode all samples at once to increase speed at the cost of VRAM usage. - x_samples = processing.decode_first_stage(shared.sd_model, samples) - x_samples = torch.clamp((x_samples + 1.0) / 2.0, min=0.0, max=1.0) - - for x_sample in x_samples: - x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) - x_sample = x_sample.astype(np.uint8) - progress_images.append(Image.fromarray(x_sample)) - - return images.image_grid(progress_images) + return images.image_grid([single_sample_to_image(sample) for sample in samples]) + def store_latent(decoded): state.current_latent = decoded diff --git a/modules/shared.py b/modules/shared.py index 95d6e225..25bfc895 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -294,7 +294,7 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"), options_templates.update(options_section(('ui', "User interface"), { "show_progressbar": OptionInfo(True, "Show progressbar"), "show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}), - "progress_decode_combined": OptionInfo(False, "Decode all progress images at once. (Slighty speeds up progress generation but consumes significantly more VRAM with large batches.)"), + "show_progress_grid": OptionInfo(True, "Show previews of all images generated in a batch as a grid"), "return_grid": OptionInfo(True, "Show grid in results for web"), "do_not_show_images": OptionInfo(False, "Do not show any images in results for web"), "add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"), diff --git a/modules/ui.py b/modules/ui.py index de0abc7e..ffa14cac 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -318,10 +318,10 @@ def check_progress_call(id_part): if shared.parallel_processing_allowed: if shared.state.sampling_step - shared.state.current_image_sampling_step >= opts.show_progress_every_n_steps and shared.state.current_latent is not None: - if opts.progress_decode_combined: - shared.state.current_image = modules.sd_samplers.samples_to_image_grid_combined(shared.state.current_latent) - else: + if opts.show_progress_grid: shared.state.current_image = modules.sd_samplers.samples_to_image_grid(shared.state.current_latent) + else: + shared.state.current_image = modules.sd_samplers.sample_to_image(shared.state.current_latent) shared.state.current_image_sampling_step = shared.state.sampling_step image = shared.state.current_image -- cgit v1.2.3 From b38370275275bf6e11575000f39c50c6e90b1f7a Mon Sep 17 00:00:00 2001 From: ritosonn Date: Fri, 21 Oct 2022 23:46:32 +0900 Subject: fix #3145 #3093 --- modules/sd_samplers.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 0b408a70..3670b57d 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -228,7 +228,7 @@ class VanillaStableDiffusionSampler: unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]} - samples = self.launch_sampling(steps, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning)) + samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning)) return samples @@ -429,7 +429,7 @@ class KDiffusionSampler: self.model_wrap_cfg.init_latent = x self.last_latent = x - samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, xi, extra_args={ + samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args={ 'cond': conditioning, 'image_cond': image_conditioning, 'uncond': unconditional_conditioning, -- cgit v1.2.3 From de1dc0d279a877d5d9f512befe30a7d7e5cf3881 Mon Sep 17 00:00:00 2001 From: Martin Cairns <4314538+MartinCairnsSQL@users.noreply.github.com> Date: Sat, 29 Oct 2022 15:23:19 +0100 Subject: Add adjust_steps_if_invalid to find next valid step for ddim uniform sampler --- modules/sd_samplers.py | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 3670b57d..aca014e8 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -1,5 +1,6 @@ from collections import namedtuple import numpy as np +from math import floor import torch import tqdm from PIL import Image @@ -205,17 +206,22 @@ class VanillaStableDiffusionSampler: self.mask = p.mask if hasattr(p, 'mask') else None self.nmask = p.nmask if hasattr(p, 'nmask') else None + + def adjust_steps_if_invalid(self, p, num_steps): + if self.config.name == 'DDIM' and p.ddim_discretize == 'uniform': + valid_step = 999 / (1000 // num_steps) + if valid_step == floor(valid_step): + return int(valid_step) + 1 + + return num_steps + + def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None): steps, t_enc = setup_img2img_steps(p, steps) - + steps = self.adjust_steps_if_invalid(p, steps) self.initialize(p) - # existing code fails with certain step counts, like 9 - try: - self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False) - except Exception: - self.sampler.make_schedule(ddim_num_steps=steps+1, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False) - + self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False) x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise) self.init_latent = x @@ -239,18 +245,14 @@ class VanillaStableDiffusionSampler: self.last_latent = x self.step = 0 - steps = steps or p.steps + steps = self.adjust_steps_if_invalid(p, 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]) - except Exception: - samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps+1, 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]) + 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]) return samples_ddim -- cgit v1.2.3 From 34c86c12b0a9d650d4e7c5be478bca34ad8ed048 Mon Sep 17 00:00:00 2001 From: Martin Cairns <4314538+MartinCairnsSQL@users.noreply.github.com> Date: Sun, 30 Oct 2022 11:04:27 +0000 Subject: Include PLMS in adjust steps as it also can fail in the same way --- modules/sd_samplers.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index aca014e8..8772db56 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -208,7 +208,7 @@ class VanillaStableDiffusionSampler: def adjust_steps_if_invalid(self, p, num_steps): - if self.config.name == 'DDIM' and p.ddim_discretize == 'uniform': + if (self.config.name == 'DDIM' and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS'): valid_step = 999 / (1000 // num_steps) if valid_step == floor(valid_step): return int(valid_step) + 1 -- cgit v1.2.3 From 8ae0ea9deaa5a09d1e0aa8b2f8e97c38d71cdbda Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Sun, 30 Oct 2022 23:48:33 +0000 Subject: Add callback to sd_samplers --- modules/sd_samplers.py | 3 +++ 1 file changed, 3 insertions(+) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 3670b57d..30cb5c4b 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -11,6 +11,7 @@ from modules import prompt_parser, devices, processing, images from modules.shared import opts, cmd_opts, state import modules.shared as shared +from modules.script_callbacks import CGFDenoiserParams, cfg_denoiser_callback SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options']) @@ -278,6 +279,8 @@ class CFGDenoiser(torch.nn.Module): 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]) + cfg_denoiser_callback(CGFDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)) + if tensor.shape[1] == uncond.shape[1]: cond_in = torch.cat([tensor, uncond]) -- cgit v1.2.3 From 5b6bedf6f2ebacb7f1f5809af8e26a6a1af16e2a Mon Sep 17 00:00:00 2001 From: DepFA <35278260+dfaker@users.noreply.github.com> Date: Wed, 2 Nov 2022 00:38:17 +0000 Subject: Update class name and assign back to vars --- modules/sd_samplers.py | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 30cb5c4b..ebc0d896 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -11,7 +11,7 @@ from modules import prompt_parser, devices, processing, images from modules.shared import opts, cmd_opts, state import modules.shared as shared -from modules.script_callbacks import CGFDenoiserParams, cfg_denoiser_callback +from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options']) @@ -279,7 +279,11 @@ class CFGDenoiser(torch.nn.Module): 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]) - cfg_denoiser_callback(CGFDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)) + denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps) + cfg_denoiser_callback(denoiser_params) + x_in = denoiser_params.x + image_cond_in = denoiser_params.image_cond + sigma_in = denoiser_params.sigma if tensor.shape[1] == uncond.shape[1]: cond_in = torch.cat([tensor, uncond]) -- cgit v1.2.3 From 9c67408004ed132637d10321bf44565f82055fd2 Mon Sep 17 00:00:00 2001 From: timntorres <116157310+timntorres@users.noreply.github.com> Date: Wed, 2 Nov 2022 02:18:21 -0700 Subject: Allow saving "before-highres-fix. (#4150) * Save image/s before doing highres fix. --- modules/processing.py | 17 +++++++++++++++-- modules/sd_samplers.py | 5 ++--- modules/shared.py | 1 + 3 files changed, 18 insertions(+), 5 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/processing.py b/modules/processing.py index b541ee2b..2dcf4879 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -521,7 +521,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: shared.state.job = f"Batch {n+1} out of {p.n_iter}" with devices.autocast(): - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength) + # Only Txt2Img needs an extra argument, n, when saving intermediate images pre highres fix. + if isinstance(p, StableDiffusionProcessingTxt2Img): + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, n=n) + else: + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength) samples_ddim = samples_ddim.to(devices.dtype_vae) x_samples_ddim = decode_first_stage(p.sd_model, samples_ddim) @@ -649,7 +653,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, n=0): self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model) if not self.enable_hr: @@ -685,6 +689,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples)) + # Save a copy of the image/s before doing highres fix, if applicable. + if opts.save and not self.do_not_save_samples and opts.save_images_before_highres_fix: + for i in range(self.batch_size): + # This batch's ith image. + img = sd_samplers.sample_to_image(samples, i) + # Index that accounts for both batch size and batch count. + ind = i + self.batch_size*n + images.save_image(img, self.outpath_samples, "", self.all_seeds[ind], self.all_prompts[ind], opts.samples_format, suffix=f"-before-highres-fix") + shared.state.nextjob() self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model) diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 44d4c189..d7fa89a0 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -93,9 +93,8 @@ def single_sample_to_image(sample): return Image.fromarray(x_sample) -def sample_to_image(samples): - return single_sample_to_image(samples[0]) - +def sample_to_image(samples, index=0): + return single_sample_to_image(samples[index]) def samples_to_image_grid(samples): return images.image_grid([single_sample_to_image(sample) for sample in samples]) diff --git a/modules/shared.py b/modules/shared.py index e65f6080..ce991424 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -255,6 +255,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "enable_pnginfo": OptionInfo(True, "Save text information about generation parameters as chunks to png files"), "save_txt": OptionInfo(False, "Create a text file next to every image with generation parameters."), "save_images_before_face_restoration": OptionInfo(False, "Save a copy of image before doing face restoration."), + "save_images_before_highres_fix": OptionInfo(False, "Save a copy of image before applying highres fix."), "jpeg_quality": OptionInfo(80, "Quality for saved jpeg images", gr.Slider, {"minimum": 1, "maximum": 100, "step": 1}), "export_for_4chan": OptionInfo(True, "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG"), -- cgit v1.2.3 From eb5e82c7ddf5e72fa13b83bd1f12d3a07a4de1a4 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Wed, 2 Nov 2022 12:45:03 +0300 Subject: do not unnecessarily run VAE one more time when saving intermediate image with hires fix --- modules/processing.py | 39 ++++++++++++++++++++------------------- modules/sd_samplers.py | 1 + modules/shared.py | 2 +- scripts/img2imgalt.py | 3 +-- 4 files changed, 23 insertions(+), 22 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/processing.py b/modules/processing.py index 2dcf4879..3a364b5f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -199,7 +199,7 @@ class StableDiffusionProcessing(): def init(self, all_prompts, all_seeds, all_subseeds): pass - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): raise NotImplementedError() def close(self): @@ -521,11 +521,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: shared.state.job = f"Batch {n+1} out of {p.n_iter}" with devices.autocast(): - # Only Txt2Img needs an extra argument, n, when saving intermediate images pre highres fix. - if isinstance(p, StableDiffusionProcessingTxt2Img): - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, n=n) - else: - samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength) + samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength, prompts=prompts) samples_ddim = samples_ddim.to(devices.dtype_vae) x_samples_ddim = decode_first_stage(p.sd_model, samples_ddim) @@ -653,7 +649,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, n=0): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model) if not self.enable_hr: @@ -666,9 +662,21 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2] + """saves image before applying hires fix, if enabled in options; takes as an arguyment either an image or batch with latent space images""" + def save_intermediate(image, index): + if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix: + return + + if not isinstance(image, Image.Image): + image = sd_samplers.sample_to_image(image, index) + + images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix") + if opts.use_scale_latent_for_hires_fix: samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear") + for i in range(samples.shape[0]): + save_intermediate(samples, i) else: decoded_samples = decode_first_stage(self.sd_model, samples) lowres_samples = torch.clamp((decoded_samples + 1.0) / 2.0, min=0.0, max=1.0) @@ -678,6 +686,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2) x_sample = x_sample.astype(np.uint8) image = Image.fromarray(x_sample) + + save_intermediate(image, i) + image = images.resize_image(0, image, self.width, self.height) image = np.array(image).astype(np.float32) / 255.0 image = np.moveaxis(image, 2, 0) @@ -689,15 +700,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples)) - # Save a copy of the image/s before doing highres fix, if applicable. - if opts.save and not self.do_not_save_samples and opts.save_images_before_highres_fix: - for i in range(self.batch_size): - # This batch's ith image. - img = sd_samplers.sample_to_image(samples, i) - # Index that accounts for both batch size and batch count. - ind = i + self.batch_size*n - images.save_image(img, self.outpath_samples, "", self.all_seeds[ind], self.all_prompts[ind], opts.samples_format, suffix=f"-before-highres-fix") - shared.state.nextjob() self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model) @@ -844,8 +846,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): self.image_conditioning = self.img2img_image_conditioning(image, self.init_latent, self.image_mask) - - def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): + def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self) samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning) @@ -856,4 +857,4 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): del x devices.torch_gc() - return samples \ No newline at end of file + return samples diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index d7fa89a0..c7c414ef 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -96,6 +96,7 @@ def single_sample_to_image(sample): def sample_to_image(samples, index=0): return single_sample_to_image(samples[index]) + def samples_to_image_grid(samples): return images.image_grid([single_sample_to_image(sample) for sample in samples]) diff --git a/modules/shared.py b/modules/shared.py index ce991424..01f47e38 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -256,6 +256,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids" "save_txt": OptionInfo(False, "Create a text file next to every image with generation parameters."), "save_images_before_face_restoration": OptionInfo(False, "Save a copy of image before doing face restoration."), "save_images_before_highres_fix": OptionInfo(False, "Save a copy of image before applying highres fix."), + "save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"), "jpeg_quality": OptionInfo(80, "Quality for saved jpeg images", gr.Slider, {"minimum": 1, "maximum": 100, "step": 1}), "export_for_4chan": OptionInfo(True, "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG"), @@ -322,7 +323,6 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "sd_hypernetwork_strength": OptionInfo(1.0, "Hypernetwork strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.001}), "inpainting_mask_weight": OptionInfo(1.0, "Inpainting conditioning mask strength", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}), "img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."), - "save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"), "img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."), "enable_quantization": OptionInfo(False, "Enable quantization in K samplers for sharper and cleaner results. This may change existing seeds. Requires restart to apply."), "enable_emphasis": OptionInfo(True, "Emphasis: use (text) to make model pay more attention to text and [text] to make it pay less attention"), diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py index 88abc093..964b75c7 100644 --- a/scripts/img2imgalt.py +++ b/scripts/img2imgalt.py @@ -166,8 +166,7 @@ class Script(scripts.Script): if override_strength: p.denoising_strength = 1.0 - - def sample_extra(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength): + def sample_extra(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts): lat = (p.init_latent.cpu().numpy() * 10).astype(int) same_params = self.cache is not None and self.cache.cfg_scale == cfg and self.cache.steps == st \ -- cgit v1.2.3 From 6008c0773ea575353f9b87da8a58454e20cc7857 Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Fri, 4 Nov 2022 23:03:05 +0000 Subject: Add support for new DPM-Solver++ samplers --- modules/sd_samplers.py | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index c7c414ef..7ece6556 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -29,6 +29,10 @@ samplers_k_diffusion = [ ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}), ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras'}), ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}), + ('DPM-Solver++(2S) a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), + ('DPM-Solver++(2M)', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), + ('DPM-Solver++(2S) Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), + ('DPM-Solver++(2M) Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), ] samplers_data_k_diffusion = [ -- cgit v1.2.3 From f92dc505a013af9e385c7edbdf97539be62503d6 Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Fri, 4 Nov 2022 23:12:48 +0000 Subject: Fix name --- modules/sd_samplers.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 7ece6556..b28a2e4c 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -31,7 +31,7 @@ samplers_k_diffusion = [ ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}), ('DPM-Solver++(2S) a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), ('DPM-Solver++(2M)', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), - ('DPM-Solver++(2S) Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), + ('DPM-Solver++(2S) a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), ('DPM-Solver++(2M) Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), ] -- cgit v1.2.3 From 1b6c2fc749e12f12bbee4705e65f217d23fa9072 Mon Sep 17 00:00:00 2001 From: hentailord85ez <112723046+hentailord85ez@users.noreply.github.com> Date: Fri, 4 Nov 2022 23:28:13 +0000 Subject: Reorder samplers --- modules/sd_samplers.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index b28a2e4c..1e88f7ee 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -24,13 +24,13 @@ samplers_k_diffusion = [ ('Heun', 'sample_heun', ['k_heun'], {}), ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {}), ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {}), + ('DPM-Solver++(2S) a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), + ('DPM-Solver++(2M)', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}), ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}), ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}), ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras'}), ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}), - ('DPM-Solver++(2S) a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), - ('DPM-Solver++(2M)', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), ('DPM-Solver++(2S) a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), ('DPM-Solver++(2M) Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), ] -- cgit v1.2.3 From 159475e072f2ed3db8235aab9c3fa18640b93b80 Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Sat, 5 Nov 2022 18:32:22 +0300 Subject: tweak names a bit for new samplers --- modules/sd_samplers.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 1e88f7ee..783992d2 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -24,15 +24,15 @@ samplers_k_diffusion = [ ('Heun', 'sample_heun', ['k_heun'], {}), ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {}), ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {}), - ('DPM-Solver++(2S) a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), - ('DPM-Solver++(2M)', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), + ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}), + ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}), ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}), ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}), ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}), ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras'}), ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}), - ('DPM-Solver++(2S) a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), - ('DPM-Solver++(2M) Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), + ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}), + ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}), ] samplers_data_k_diffusion = [ -- cgit v1.2.3 From cdc8020d13c5eef099c609b0a911ccf3568afc0d Mon Sep 17 00:00:00 2001 From: AUTOMATIC <16777216c@gmail.com> Date: Sat, 19 Nov 2022 12:01:51 +0300 Subject: change StableDiffusionProcessing to internally use sampler name instead of sampler index --- modules/api/api.py | 26 ++++++++--------------- modules/hypernetworks/hypernetwork.py | 4 ++-- modules/images.py | 2 +- modules/img2img.py | 4 ++-- modules/processing.py | 29 +++++++++++--------------- modules/sd_samplers.py | 13 +++++++++--- modules/textual_inversion/textual_inversion.py | 4 ++-- modules/txt2img.py | 3 ++- modules/ui.py | 2 +- scripts/img2imgalt.py | 4 ++-- scripts/xy_grid.py | 12 +++++------ 11 files changed, 49 insertions(+), 54 deletions(-) (limited to 'modules/sd_samplers.py') diff --git a/modules/api/api.py b/modules/api/api.py index 596a6616..0eccccbb 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -6,9 +6,9 @@ from threading import Lock from gradio.processing_utils import encode_pil_to_base64, decode_base64_to_file, decode_base64_to_image from fastapi import APIRouter, Depends, FastAPI, HTTPException import modules.shared as shared +from modules import sd_samplers from modules.api.models import * from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images -from modules.sd_samplers import all_samplers from modules.extras import run_extras, run_pnginfo from PIL import PngImagePlugin from modules.sd_models import checkpoints_list @@ -25,8 +25,12 @@ def upscaler_to_index(name: str): raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be on of these: {' , '.join([x.name for x in sd_upscalers])}") -sampler_to_index = lambda name: next(filter(lambda row: name.lower() == row[1].name.lower(), enumerate(all_samplers)), None) +def validate_sampler_name(name): + config = sd_samplers.all_samplers_map.get(name, None) + if config is None: + raise HTTPException(status_code=404, detail="Sampler not found") + return name def setUpscalers(req: dict): reqDict = vars(req) @@ -82,14 +86,9 @@ class Api: self.app.add_api_route("/sdapi/v1/artists", self.get_artists, methods=["GET"], response_model=List[ArtistItem]) def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI): - sampler_index = sampler_to_index(txt2imgreq.sampler_index) - - if sampler_index is None: - raise HTTPException(status_code=404, detail="Sampler not found") - populate = txt2imgreq.copy(update={ # Override __init__ params "sd_model": shared.sd_model, - "sampler_index": sampler_index[0], + "sampler_name": validate_sampler_name(txt2imgreq.sampler_index), "do_not_save_samples": True, "do_not_save_grid": True } @@ -109,12 +108,6 @@ class Api: return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js()) def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI): - sampler_index = sampler_to_index(img2imgreq.sampler_index) - - if sampler_index is None: - raise HTTPException(status_code=404, detail="Sampler not found") - - init_images = img2imgreq.init_images if init_images is None: raise HTTPException(status_code=404, detail="Init image not found") @@ -123,10 +116,9 @@ class Api: if mask: mask = decode_base64_to_image(mask) - populate = img2imgreq.copy(update={ # Override __init__ params "sd_model": shared.sd_model, - "sampler_index": sampler_index[0], + "sampler_name": validate_sampler_name(img2imgreq.sampler_index), "do_not_save_samples": True, "do_not_save_grid": True, "mask": mask @@ -272,7 +264,7 @@ class Api: return vars(shared.cmd_opts) def get_samplers(self): - return [{"name":sampler[0], "aliases":sampler[2], "options":sampler[3]} for sampler in all_samplers] + return [{"name":sampler[0], "aliases":sampler[2], "options":sampler[3]} for sampler in sd_samplers.all_samplers] def get_upscalers(self): upscalers = [] diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 7f182712..fbb87dd1 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -12,7 +12,7 @@ import torch import tqdm from einops import rearrange, repeat from ldm.util import default -from modules import devices, processing, sd_models, shared +from modules import devices, processing, sd_models, shared, sd_samplers from modules.textual_inversion import textual_inversion from modules.textual_inversion.learn_schedule import LearnRateScheduler from torch import einsum @@ -535,7 +535,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log p.prompt = preview_prompt p.negative_prompt = preview_negative_prompt p.steps = preview_steps - p.sampler_index = preview_sampler_index + p.sampler_name = sd_samplers.samplers[preview_sampler_index].name p.cfg_scale = preview_cfg_scale p.seed = preview_seed p.width = preview_width diff --git a/modules/images.py b/modules/images.py index ae705cbd..26d5b7a9 100644 --- a/modules/images.py +++ b/modules/images.py @@ -303,7 +303,7 @@ class FilenameGenerator: 'width': lambda self: self.image.width, 'height': lambda self: self.image.height, 'styles': lambda self: self.p and sanitize_filename_part(", ".join([style for style in self.p.styles if not style == "None"]) or "None", replace_spaces=False), - 'sampler': lambda self: self.p and sanitize_filename_part(sd_samplers.samplers[self.p.sampler_index].name, replace_spaces=False), + 'sampler': lambda self: self.p and sanitize_filename_part(self.p.sampler_name, replace_spaces=False), 'model_hash': lambda self: getattr(self.p, "sd_model_hash", shared.sd_model.sd_model_hash), 'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'), 'datetime': lambda self, *args: self.datetime(*args), # accepts formats: [datetime], [datetime], [datetime