diff options
Diffstat (limited to 'modules/processing.py')
| -rw-r--r-- | modules/processing.py | 123 |
1 files changed, 96 insertions, 27 deletions
diff --git a/modules/processing.py b/modules/processing.py index 6f01c95f..7789f9a4 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -62,18 +62,22 @@ def apply_color_correction(correction, original_image): return image.convert('RGB')
-def apply_overlay(image, paste_loc, index, overlays):
- if overlays is None or index >= len(overlays):
- return image
+def uncrop(image, dest_size, paste_loc):
+ x, y, w, h = paste_loc
+ base_image = Image.new('RGBA', dest_size)
+ image = images.resize_image(1, image, w, h)
+ base_image.paste(image, (x, y))
+ image = base_image
+
+ return image
- overlay = overlays[index]
+
+def apply_overlay(image, paste_loc, overlay):
+ if overlay is None:
+ return image
if paste_loc is not None:
- x, y, w, h = paste_loc
- base_image = Image.new('RGBA', (overlay.width, overlay.height))
- image = images.resize_image(1, image, w, h)
- base_image.paste(image, (x, y))
- image = base_image
+ image = uncrop(image, (overlay.width, overlay.height), paste_loc)
image = image.convert('RGBA')
image.alpha_composite(overlay)
@@ -81,9 +85,12 @@ def apply_overlay(image, paste_loc, index, overlays): return image
-def create_binary_mask(image):
+def create_binary_mask(image, round=True):
if image.mode == 'RGBA' and image.getextrema()[-1] != (255, 255):
- image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+ if round:
+ image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+ else:
+ image = image.split()[-1].convert("L")
else:
image = image.convert('L')
return image
@@ -106,6 +113,21 @@ 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()
+ diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
+ if diffusion_model_input is not None:
+ if diffusion_model_input.shape[1] == 9:
+ # The "masked-image" in this case will just be all 0.5 since the entire image is masked.
+ 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.
+ image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+ image_conditioning = image_conditioning.to(x.dtype)
+
+ 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.
# Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
@@ -308,7 +330,7 @@ class StableDiffusionProcessing: c_adm = torch.cat((c_adm, noise_level_emb), 1)
return c_adm
- def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None):
+ def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None, round_image_mask=True):
self.is_using_inpainting_conditioning = True
# Handle the different mask inputs
@@ -320,8 +342,10 @@ class StableDiffusionProcessing: 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)
+ if round_image_mask:
+ # Caller is requesting a discretized mask as input, so we round to either 1.0 or 0.0
+ conditioning_mask = torch.round(conditioning_mask)
+
else:
conditioning_mask = source_image.new_ones(1, 1, *source_image.shape[-2:])
@@ -345,7 +369,7 @@ class StableDiffusionProcessing: return image_conditioning
- def img2img_image_conditioning(self, source_image, latent_image, image_mask=None):
+ def img2img_image_conditioning(self, source_image, latent_image, image_mask=None, round_image_mask=True):
source_image = devices.cond_cast_float(source_image)
# HACK: Using introspection as the Depth2Image model doesn't appear to uniquely
@@ -357,11 +381,17 @@ class StableDiffusionProcessing: return self.edit_image_conditioning(source_image)
if self.sampler.conditioning_key in {'hybrid', 'concat'}:
- return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
+ return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask, round_image_mask=round_image_mask)
if self.sampler.conditioning_key == "crossattn-adm":
return self.unclip_image_conditioning(source_image)
+ sd = self.sampler.model_wrap.inner_model.model.state_dict()
+ diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
+ 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)
@@ -422,6 +452,8 @@ class StableDiffusionProcessing: opts.sdxl_crop_top,
self.width,
self.height,
+ opts.fp8_storage,
+ opts.cache_fp16_weight,
)
def get_conds_with_caching(self, function, required_prompts, steps, caches, extra_network_data, hires_steps=None):
@@ -679,6 +711,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Size": f"{p.width}x{p.height}",
"Model hash": p.sd_model_hash if opts.add_model_hash_to_info else None,
"Model": p.sd_model_name if opts.add_model_name_to_info else None,
+ "FP8 weight": opts.fp8_storage if devices.fp8 else None,
+ "Cache FP16 weight for LoRA": opts.cache_fp16_weight if devices.fp8 else None,
"VAE hash": p.sd_vae_hash if opts.add_vae_hash_to_info else None,
"VAE": p.sd_vae_name if opts.add_vae_name_to_info else None,
"Variation seed": (None if p.subseed_strength == 0 else (p.all_subseeds[0] if use_main_prompt else all_subseeds[index])),
@@ -867,6 +901,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
+ if p.scripts is not None:
+ ps = scripts.PostSampleArgs(samples_ddim)
+ p.scripts.post_sample(p, ps)
+ samples_ddim = ps.samples
+
if getattr(samples_ddim, 'already_decoded', False):
x_samples_ddim = samples_ddim
else:
@@ -922,13 +961,31 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: pp = scripts.PostprocessImageArgs(image)
p.scripts.postprocess_image(p, pp)
image = pp.image
+
+ mask_for_overlay = getattr(p, "mask_for_overlay", None)
+ overlay_image = p.overlay_images[i] if getattr(p, "overlay_images", None) is not None and i < len(p.overlay_images) else None
+
+ if p.scripts is not None:
+ ppmo = scripts.PostProcessMaskOverlayArgs(i, mask_for_overlay, overlay_image)
+ p.scripts.postprocess_maskoverlay(p, ppmo)
+ mask_for_overlay, overlay_image = ppmo.mask_for_overlay, ppmo.overlay_image
+
if p.color_corrections is not None and i < len(p.color_corrections):
if save_samples and opts.save_images_before_color_correction:
- image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
+ image_without_cc = apply_overlay(image, p.paste_to, overlay_image)
images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-color-correction")
image = apply_color_correction(p.color_corrections[i], image)
- image = apply_overlay(image, p.paste_to, i, p.overlay_images)
+ # If the intention is to show the output from the model
+ # that is being composited over the original image,
+ # we need to keep the original image around
+ # and use it in the composite step.
+ original_denoised_image = image.copy()
+
+ if p.paste_to is not None:
+ original_denoised_image = uncrop(original_denoised_image, (overlay_image.width, overlay_image.height), p.paste_to)
+
+ image = apply_overlay(image, p.paste_to, overlay_image)
if save_samples:
images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p)
@@ -938,16 +995,17 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: if opts.enable_pnginfo:
image.info["parameters"] = text
output_images.append(image)
- if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay:
+
+ if mask_for_overlay is not None:
if opts.return_mask or opts.save_mask:
- image_mask = p.mask_for_overlay.convert('RGB')
+ image_mask = mask_for_overlay.convert('RGB')
if save_samples and opts.save_mask:
images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask")
if opts.return_mask:
output_images.append(image_mask)
if opts.return_mask_composite or opts.save_mask_composite:
- image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
+ image_mask_composite = Image.composite(original_denoised_image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
if save_samples and opts.save_mask_composite:
images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask-composite")
if opts.return_mask_composite:
@@ -1025,6 +1083,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): hr_sampler_name: str = None
hr_prompt: str = ''
hr_negative_prompt: str = ''
+ force_task_id: str = None
cached_hr_uc = [None, None]
cached_hr_c = [None, None]
@@ -1097,7 +1156,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing): def init(self, all_prompts, all_seeds, all_subseeds):
if self.enable_hr:
- if self.hr_checkpoint_name:
+ if self.hr_checkpoint_name and self.hr_checkpoint_name != 'Use same checkpoint':
self.hr_checkpoint_info = sd_models.get_closet_checkpoint_match(self.hr_checkpoint_name)
if self.hr_checkpoint_info is None:
@@ -1351,12 +1410,14 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): mask_blur_x: int = 4
mask_blur_y: int = 4
mask_blur: int = None
+ mask_round: bool = True
inpainting_fill: int = 0
inpaint_full_res: bool = True
inpaint_full_res_padding: int = 0
inpainting_mask_invert: int = 0
initial_noise_multiplier: float = None
latent_mask: Image = None
+ force_task_id: str = None
image_mask: Any = field(default=None, init=False)
@@ -1396,7 +1457,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): if image_mask is not None:
# image_mask is passed in as RGBA by Gradio to support alpha masks,
# but we still want to support binary masks.
- image_mask = create_binary_mask(image_mask)
+ image_mask = create_binary_mask(image_mask, round=self.mask_round)
if self.inpainting_mask_invert:
image_mask = ImageOps.invert(image_mask)
@@ -1442,7 +1503,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): # Save init image
if opts.save_init_img:
self.init_img_hash = hashlib.md5(img.tobytes()).hexdigest()
- images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False)
+ images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False, existing_info=img.info)
image = images.flatten(img, opts.img2img_background_color)
@@ -1503,7 +1564,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): latmask = init_mask.convert('RGB').resize((self.init_latent.shape[3], self.init_latent.shape[2]))
latmask = np.moveaxis(np.array(latmask, dtype=np.float32), 2, 0) / 255
latmask = latmask[0]
- latmask = np.around(latmask)
+ if self.mask_round:
+ latmask = np.around(latmask)
latmask = np.tile(latmask[None], (4, 1, 1))
self.mask = torch.asarray(1.0 - latmask).to(shared.device).type(self.sd_model.dtype)
@@ -1515,7 +1577,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): elif self.inpainting_fill == 3:
self.init_latent = self.init_latent * self.mask
- self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask)
+ self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask, self.mask_round)
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
x = self.rng.next()
@@ -1527,7 +1589,14 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
if self.mask is not None:
- samples = samples * self.nmask + self.init_latent * self.mask
+ blended_samples = samples * self.nmask + self.init_latent * self.mask
+
+ if self.scripts is not None:
+ mba = scripts.MaskBlendArgs(samples, self.nmask, self.init_latent, self.mask, blended_samples)
+ self.scripts.on_mask_blend(self, mba)
+ blended_samples = mba.blended_latent
+
+ samples = blended_samples
del x
devices.torch_gc()
|