diff options
Diffstat (limited to 'modules/processing.py')
| -rw-r--r-- | modules/processing.py | 46 |
1 files changed, 38 insertions, 8 deletions
diff --git a/modules/processing.py b/modules/processing.py index c310df6a..0417ffc5 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -21,7 +21,10 @@ import modules.face_restoration import modules.images as images
import modules.styles
import logging
+from ldm.data.util import AddMiDaS
+from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
+from einops import repeat, rearrange
# some of those options should not be changed at all because they would break the model, so I removed them from options.
opt_C = 4
@@ -74,7 +77,7 @@ class StableDiffusionProcessing(): """
def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, sampler_index: int = None):
if sampler_index is not None:
- warnings.warn("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name")
+ print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
self.sd_model = sd_model
self.outpath_samples: str = outpath_samples
@@ -150,11 +153,26 @@ class StableDiffusionProcessing(): return image_conditioning
- def img2img_image_conditioning(self, source_image, latent_image, image_mask = None):
- if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
- # Dummy zero conditioning if we're not using inpainting model.
- return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
+ def depth2img_image_conditioning(self, source_image):
+ # Use the AddMiDaS helper to Format our source image to suit the MiDaS model
+ transformer = AddMiDaS(model_type="dpt_hybrid")
+ transformed = transformer({"jpg": rearrange(source_image[0], "c h w -> h w c")})
+ midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
+ midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
+
+ conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
+ conditioning = torch.nn.functional.interpolate(
+ self.sd_model.depth_model(midas_in),
+ size=conditioning_image.shape[2:],
+ mode="bicubic",
+ align_corners=False,
+ )
+
+ (depth_min, depth_max) = torch.aminmax(conditioning)
+ conditioning = 2. * (conditioning - depth_min) / (depth_max - depth_min) - 1.
+ return conditioning
+ def inpainting_image_conditioning(self, source_image, latent_image, image_mask = None):
self.is_using_inpainting_conditioning = True
# Handle the different mask inputs
@@ -191,6 +209,18 @@ class StableDiffusionProcessing(): return image_conditioning
+ def img2img_image_conditioning(self, source_image, latent_image, image_mask=None):
+ # HACK: Using introspection as the Depth2Image model doesn't appear to uniquely
+ # identify itself with a field common to all models. The conditioning_key is also hybrid.
+ if isinstance(self.sd_model, LatentDepth2ImageDiffusion):
+ return self.depth2img_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)
+
+ # Dummy zero conditioning if we're not using inpainting or depth model.
+ return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)
+
def init(self, all_prompts, all_seeds, all_subseeds):
pass
@@ -414,7 +444,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration generation_params_text = ", ".join([k if k == v else f'{k}: {generation_parameters_copypaste.quote(v)}' for k, v in generation_params.items() if v is not None])
- negative_prompt_text = "\nNegative prompt: " + p.all_negative_prompts[0] if p.all_negative_prompts[0] else ""
+ negative_prompt_text = "\nNegative prompt: " + p.all_negative_prompts[index] if p.all_negative_prompts[index] else ""
return f"{all_prompts[index]}{negative_prompt_text}\n{generation_params_text}".strip()
@@ -530,8 +560,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: with devices.autocast():
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)
+ x_samples_ddim = [decode_first_stage(p.sd_model, samples_ddim[i:i+1].to(dtype=devices.dtype_vae))[0].cpu() for i in range(samples_ddim.size(0))]
+ x_samples_ddim = torch.stack(x_samples_ddim).float()
x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
del samples_ddim
|