Skip to content

fix a few issues in controlnet inpaint pipelines #5470

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 23, 2023
Merged

fix a few issues in controlnet inpaint pipelines #5470

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
51139a7
add
Oct 20, 2023
e64b006
Update docs/source/en/api/pipelines/controlnet_sdxl.md
yiyixuxu Oct 23, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions docs/source/en/api/pipelines/controlnet_sdxl.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,15 @@ Make sure to check out the Schedulers [guide](/using-diffusers/schedulers) to le
- all
- __call__

## StableDiffusionXLControlNetImg2ImgPipeline
[[autodoc]] StableDiffusionXLControlNetImg2ImgPipeline
- all
- __call__

## StableDiffusionXLControlNetInpaintPipeline
[[autodoc]] StableDiffusionXLControlNetInpaintPipeline
- all
- __call__
## StableDiffusionPipelineOutput

[[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput
16 changes: 7 additions & 9 deletions src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,18 +65,16 @@
>>> mask_image = mask_image.resize((512, 512))


>>> def make_inpaint_condition(image, image_mask):
... image = np.array(image.convert("RGB")).astype(np.float32) / 255.0
... image_mask = np.array(image_mask.convert("L")).astype(np.float32) / 255.0

... assert image.shape[0:1] == image_mask.shape[0:1], "image and image_mask must have the same image size"
... image[image_mask > 0.5] = -1.0 # set as masked pixel
... image = np.expand_dims(image, 0).transpose(0, 3, 1, 2)
... image = torch.from_numpy(image)
>>> def make_canny_condition(image):
... image = np.array(image)
... image = cv2.Canny(image, 100, 200)
... image = image[:, :, None]
... image = np.concatenate([image, image, image], axis=2)
... image = Image.fromarray(image)
... return image


>>> control_image = make_inpaint_condition(init_image, mask_image)
>>> control_image = make_canny_condition(init_image)

>>> controlnet = ControlNetModel.from_pretrained(
... "lllyasviel/control_v11p_sd15_inpaint", torch_dtype=torch.float16
Expand Down
32 changes: 15 additions & 17 deletions src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,27 +72,24 @@
>>> mask_image = mask_image.resize((1024, 1024))


>>> def make_inpaint_condition(image, image_mask):
... image = np.array(image.convert("RGB")).astype(np.float32) / 255.0
... image_mask = np.array(image_mask.convert("L")).astype(np.float32) / 255.0

... assert image.shape[0:1] == image_mask.shape[0:1], "image and image_mask must have the same image size"
... image[image_mask < 0.5] = 0 # set as masked pixel
... image = np.expand_dims(image, 0).transpose(0, 3, 1, 2)
... image = torch.from_numpy(image)
>>> def make_canny_condition(image):
... image = np.array(image)
... image = cv2.Canny(image, 100, 200)
... image = image[:, :, None]
... image = np.concatenate([image, image, image], axis=2)
... image = Image.fromarray(image)
... return image


>>> control_image = make_inpaint_condition(init_image, mask_image)
>>> control_image = make_canny_condition(init_image)

>>> controlnet = ControlNetModel.from_pretrained(
... "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float32
... "diffusers/controlnet-canny-sdxl-1.0", torch_dtype=torch.float16
... )
>>> pipe = StableDiffusionXLControlNetInpaintPipeline.from_pretrained(
... "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, torch_dtype=torch.float32
... "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, torch_dtype=torch.float16
... )

>>> pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
>>> pipe.enable_model_cpu_offload()

>>> # generate image
Expand Down Expand Up @@ -746,13 +743,14 @@ def prepare_latents(
"However, either the image or the noise timestep has not been provided."
)

if image.shape[1] == 4:
image_latents = image.to(device=device, dtype=dtype)
elif return_image_latents or (latents is None and not is_strength_max):
if return_image_latents or (latents is None and not is_strength_max):
image = image.to(device=device, dtype=dtype)
image_latents = self._encode_vae_image(image=image, generator=generator)

image_latents = image_latents.repeat(batch_size // image_latents.shape[0], 1, 1, 1)
if image.shape[1] == 4:
image_latents = image
else:
image_latents = self._encode_vae_image(image=image, generator=generator)
image_latents = image_latents.repeat(batch_size // image_latents.shape[0], 1, 1, 1)

if latents is None and add_noise:
noise = randn_tensor(shape, generator=generator, device=device, dtype=dtype)
Expand Down