[X] I have searched the existing issues and checked the recent builds/commits
What happened?
When trying to inpaint anything, the inpainted mask is not being aggregated with the source image, instead a new image is generated, representing only a smaller region from the original larger picture, where the mask was marked.
As a side note: It looks like the inpainted (smaller) image is not generated correctly: the the whole area seems to be regenerated not only the masked region, no matter what is chosen for masked content. A separate bug report is going to be opened for it.
Steps to reproduce the problem
Img2img - Inpaint tab:
Prompt:
Wolf head pendant
Picture was uploaded and masked:
settings as below:
Result is:
What should have happened?
The generated image of the will be aggregated into the source image and the resulting image will be displayed as a result
(Automatic1111) D:\AI\A1111_dml\stable-diffusion-webui-directml>webui.bat --onnx --backend directml --medvram
venv "D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\Scripts\Python.exe"
fatal: No names found, cannot describe anything.
Python 3.10.6 | packaged by conda-forge | (main, Oct 24 2022, 16:02:16) [MSC v.1916 64 bit (AMD64)]
Version: 1.6.0
Commit hash: 7b0b721837e4e5324d64f4073b64bbd3da0755e7
Installing onnxruntime
Installing onnxruntime-directml
WARNING! Because Olive optimization does not support torch 2.0, some packages will be downgraded and it can occur version mismatches between packages. (Strongly recommend to create another virtual environment to run Olive)
Installing Olive
Launching Web UI with arguments: --onnx --backend directml --medvram
no module 'xformers'. Processing without...
No SDP backend available, likely because you are running in pytorch versions < 2.0. In fact, you are using PyTorch 1.13.1+cpu. You might want to consider upgrading.
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
==============================================================================
You are running torch 1.13.1+cpu.
The program is tested to work with torch 2.0.0.
To reinstall the desired version, run with commandline flag --reinstall-torch.
Beware that this will cause a lot of large files to be downloaded, as well as
there are reports of issues with training tab on the latest version.
Use --skip-version-check commandline argument to disable this check.
==============================================================================
2023-09-26 09:27:49,217 - ControlNet - INFO - ControlNet v1.1.410
ControlNet preprocessor location: D:\AI\A1111_dml\stable-diffusion-webui-directml\extensions\sd-webui-controlnet\annotator\downloads
2023-09-26 09:27:49,325 - ControlNet - INFO - ControlNet v1.1.410
Model PhotoMerge [Optimized] loaded.
Applying attention optimization: InvokeAI... done.
D:\AI\A1111_dml\stable-diffusion-webui-directml\modules\ui.py:1665: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead.
with gr.Row().style(equal_height=False):
D:\AI\A1111_dml\stable-diffusion-webui-directml\modules\ui.py:1788: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead.
with gr.Row().style(equal_height=False):
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Startup time: 8.5s (prepare environment: 4.0s, import torch: 2.1s, import gradio: 1.1s, setup paths: 1.3s, initialize shared: 1.1s, other imports: 0.2s, load scripts: 1.3s, create ui: 0.7s, gradio launch: 0.2s).
Model Photon [Optimized] loaded.
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]2023-09-26 09:30:11.9554550 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:30:11.9588724 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 14%|███████▍ | 1/7 [00:00<00:01, 5.62it/s]2023-09-26 09:30:12.3379298 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:30:12.3414581 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 29%|██████████████▊ | 2/7 [00:00<00:01, 2.99it/s]2023-09-26 09:30:13.8153930 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:30:13.8190114 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 57%|█████████████████████████████▋ | 4/7 [00:02<00:02, 1.28it/s]D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
2023-09-26 09:30:14.6678387 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:30:14.6715411 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 7/7 [00:02<00:00, 2.44it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 24/24 [00:01<00:00, 15.63it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 18/18 [00:01<00:00, 17.85it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 18.09it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 17.91it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 13/13 [00:00<00:00, 18.19it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 17/17 [00:00<00:00, 17.88it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 43/43 [00:02<00:00, 17.43it/s]
Model PhotoMerge-inpainting [Optimized] loaded.
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s]2023-09-26 09:31:37.5518081 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:31:37.5552047 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 14%|███████▍ | 1/7 [00:00<00:00, 6.05it/s]2023-09-26 09:31:37.9110618 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:31:37.9145110 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 29%|██████████████▊ | 2/7 [00:00<00:01, 3.11it/s]2023-09-26 09:31:39.3775742 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:31:39.3810802 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 57%|█████████████████████████████▋ | 4/7 [00:02<00:02, 1.29it/s]D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\transformers\models\clip\feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
2023-09-26 09:31:40.2435693 [W:onnxruntime:, session_state.cc:1162 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-09-26 09:31:40.2470056 [W:onnxruntime:, session_state.cc:1164 onnxruntime::VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 7/7 [00:02<00:00, 2.46it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 35/35 [00:02<00:00, 16.23it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 19/19 [00:01<00:00, 17.47it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 19/19 [00:01<00:00, 17.27it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 28/28 [00:01<00:00, 17.46it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 48/48 [00:02<00:00, 17.50it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 57/57 [00:03<00:00, 17.33it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 57/57 [00:03<00:00, 17.52it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 39/39 [00:02<00:00, 17.45it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 43/43 [00:02<00:00, 17.59it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 34/34 [00:01<00:00, 17.56it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 28/28 [00:01<00:00, 17.46it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 28/28 [00:01<00:00, 17.47it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 28/28 [00:01<00:00, 17.40it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 28/28 [00:01<00:00, 17.22it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 43/43 [00:02<00:00, 17.58it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 39/39 [00:02<00:00, 17.51it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 39/39 [00:02<00:00, 17.47it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 36/36 [00:02<00:00, 17.31it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 36/36 [00:02<00:00, 17.07it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 36/36 [00:02<00:00, 17.33it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 29/29 [00:01<00:00, 17.55it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 25/25 [00:01<00:00, 17.55it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 25/25 [00:01<00:00, 17.54it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 31/31 [00:01<00:00, 16.40it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 31/31 [00:01<00:00, 17.49it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
warnings.warn(
100%|██████████████████████████████████████████████████████████████████████████████████| 31/31 [00:01<00:00, 17.52it/s]
D:\AI\A1111_dml\stable-diffusion-webui-directml\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_onnx_stable_diffusion_img2img.py:37: FutureWarning: The preprocess method is deprecated and will be removed in a future version. Please use VaeImageProcessor.preprocess instead
Is there an existing issue for this?
What happened?
When trying to inpaint anything, the inpainted mask is not being aggregated with the source image, instead a new image is generated, representing only a smaller region from the original larger picture, where the mask was marked.
As a side note: It looks like the inpainted (smaller) image is not generated correctly: the the whole area seems to be regenerated not only the masked region, no matter what is chosen for masked content. A separate bug report is going to be opened for it.
Steps to reproduce the problem
Img2img - Inpaint tab: Prompt: Wolf head pendant
Picture was uploaded and masked:
settings as below:
Result is:
What should have happened?
The generated image of the will be aggregated into the source image and the resulting image will be displayed as a result
Sysinfo
sysinfo-2023-09-26-07-53.txt
What browsers do you use to access the UI ?
Mozilla Firefox
Console logs
Additional information
No response