You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have searched the existing issues and checked the recent builds/commits of both this extension and the webui
What happened?
For example, I want to expand the image of a girl (only upper body, 512x512) to a full body without compromising the current details. I use "Image to Image, Resize and Fill," and enable the ControlNet inpaint to keep details. However, the result is that the image expands from the center rather than from one side. In the demonstration video, the top area of the image is not necessary.
demonstration video onedrive link:https://1drv.ms/v/s!AiY-RHw-0-RVinVeT_NGgk-CcpXL?e=FMUgWv
1.I sent it to "Image to Image," then I clicked the edit button to optimize the image edge.
2.After that, I clicked auto-detection to optimize the resolution, but it didn't work. So I double-clicked the image and tried auto-3.detection again, and it worked.
4.I set the resize mode, denoise strength to 1, enabled the ControlNet inpaint, set the resize mode, and checked "ControlNet is more important."
5.I generated the image.
What should have happened?
2.The result is that the image expanded from the center, not from one side. In the demonstrative video, the top area of the image is not necessary.
Commit where the problem happens
webui: version: v1.5.2 • python: 3.10.12 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.32.0 • checkpoint: fe54b5d04d
controlnet: version v1.1.238 main | 0cfc88b | Mon Aug 14 00:07:03 2023
Is there an existing issue for this?
What happened?
For example, I want to expand the image of a girl (only upper body, 512x512) to a full body without compromising the current details. I use "Image to Image, Resize and Fill," and enable the ControlNet inpaint to keep details. However, the result is that the image expands from the center rather than from one side. In the demonstration video, the top area of the image is not necessary.
demonstration video onedrive link:https://1drv.ms/v/s!AiY-RHw-0-RVinVeT_NGgk-CcpXL?e=FMUgWv
same issue in sd webui: AUTOMATIC1111/stable-diffusion-webui#12789
Steps to reproduce the problem
1.I sent it to "Image to Image," then I clicked the edit button to optimize the image edge.
2.After that, I clicked auto-detection to optimize the resolution, but it didn't work. So I double-clicked the image and tried auto-3.detection again, and it worked.
4.I set the resize mode, denoise strength to 1, enabled the ControlNet inpaint, set the resize mode, and checked "ControlNet is more important."
5.I generated the image.
What should have happened?
2.The result is that the image expanded from the center, not from one side. In the demonstrative video, the top area of the image is not necessary.
Commit where the problem happens
webui: version: v1.5.2 • python: 3.10.12 • torch: 2.0.1+cu118 • xformers: 0.0.20 • gradio: 3.32.0 • checkpoint: fe54b5d04d
controlnet: version v1.1.238 main | 0cfc88b | Mon Aug 14 00:07:03 2023
What browsers do you use to access the UI ?
Microsoft Edge
Command Line Arguments
List of enabled extensions
PBRemTools | https://github.com/mattyamonaca/PBRemTools.git | main | 91e16d32 | Tue Aug 1 10:08:11 2023
SD-CN-Animation | https://github.com/volotat/SD-CN-Animation.git | main | 2e257bbf | Tue May 30 16:49:03 2023
SadTalker | https://github.com/OpenTalker/SadTalker.git | main | bd5b64af | Sun Aug 6 04:17:40 2023
Stable-Diffusion-Webui-Civitai-Helper | https://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper.git | main | 920ca326 | Tue May 23 11:53:22 2023
a1111-sd-webui-tagcomplete | https://github.com/DominikDoom/a1111-sd-webui-tagcomplete.git | main | 5deb72cd | Wed Aug 16 08:50:05 2023
adetailer | https://github.com/Bing-su/adetailer.git | main | 22602536 | Mon Aug 14 14:45:42 2023
model-keyword | https://github.com/mix1009/model-keyword.git | main | 748674ba | Thu Aug 17 06:01:15 2023
multidiffusion-upscaler-for-automatic1111 | https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111.git | main | f9f8073e | Sat Jul 22 06:53:11 2023
sd-3dmodel-loader | https://github.com/jtydhr88/sd-3dmodel-loader.git | master | 1e01cc16 | Fri Jun 30 01:16:04 2023
sd-webui-3d-open-pose-editor | https://github.com/nonnonstop/sd-webui-3d-open-pose-editor.git | main | f2d5aac5 | Sat Apr 15 13:21:06 2023
sd-webui-controlnet | https://github.com/Mikubill/sd-webui-controlnet.git | main | 0cfc88b | Mon Aug 14 00:07:03 2023
sd-webui-openpose-editor | https://github.com/huchenlei/sd-webui-openpose-editor.git | main | d352f29e | Sat Jul 22 21:15:12 2023
sd-webui-prompt-all-in-one | https://github.com/Physton/sd-webui-prompt-all-in-one | main | 20685967 | Thu Aug 17 17:18:31 2023
sd-webui-regional-prompter | https://github.com/hako-mikan/sd-webui-regional-prompter.git | main | e75f5b96 | Thu Aug 10 15:39:08 2023
sd-webui-roop | https://github.com/s0md3v/sd-webui-roop | main | e6333fbe | Fri Jul 7 09:22:59 2023
sd_civitai_extension | https://github.com/civitai/sd_civitai_extension.git | main | 6afadb00 | Fri Aug 4 23:08:54 2023
stable-diffusion-webui-images-browser | https://github.com/AlUlkesh/stable-diffusion-webui-images-browser.git | main | 6fe65acc | Thu Aug 17 06:33:07 2023
stable-diffusion-webui-localization-zh_Hans
Console logs
Additional information
AUTOMATIC1111/stable-diffusion-webui#12789
The text was updated successfully, but these errors were encountered: