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
Hi!
Blender 4.2
I've installed everything by provided tutorial, models installed, plugin seems to be working.
Problem is that outputs are just black. First time i ran this plugin i've got this:
Loading pipeline components...: 100%|████████████████████████████████████████████████████| 6/6 [00:17<00:00, 2.96s/it]
You have disabled the safety checker for <class 'diffusers.pipelines.controlnet.pipeline_controlnet_inpaint.StableDiffusionControlNetInpaintPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at huggingface/diffusers#254 .
100%|██████████████████████████████████████████████████████████████████████████████████| 50/50 [01:02<00:00, 1.24s/it]
C:\Users\cellers\AppData\Roaming\Blender Foundation\Blender\4.2\extensions\user_default\diffused_texture_addon\diffusedtexture\process_operations.py:157: RuntimeWarning: invalid value encountered in divide
weighted_tex = np.sum(weighted_tex, axis=0) / np.stack(
C:\Users\cellers\AppData\Roaming\Blender Foundation\Blender\4.2\extensions\user_default\diffused_texture_addon\diffusedtexture\process_operations.py:172: RuntimeWarning: invalid value encountered in cast
weighted_tex.astype(np.uint8),
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_depth
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_normal
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_uv
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_position
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_img
Read blend: "D:\SD\DIFF_TEXTURE\OUT\scene_backup.blend"
Info: Saved "scene_backup.blend"`
Loading pipeline components...: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:01<00:00, 3.88it/s]
You have disabled the safety checker for <class 'diffusers.pipelines.controlnet.pipeline_controlnet_inpaint.StableDiffusionControlNetInpaintPipeline'> by passing safety_checker=None. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at huggingface/diffusers#254 .
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [01:03<00:00, 1.28s/it]
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_depth
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_normal
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_uv
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_position
Deleted folder: D:\SD\DIFF_TEXTURE\OUT\first_pass_img
Read blend: "D:\SD\DIFF_TEXTURE\OUT\scene_backup.blend"`
These are the settings:
P.S. I would love to use custom checkpoints and CNet models to adjust art style
We would need more controls for this - steps, cfg scale, etc.
The text was updated successfully, but these errors were encountered:
Can you check if the output texture itself is black, or just the model in the viewport?
In your output folder "D:\SD\DIFF_TEXTURE\OUT" should be a .png file "first_pass.png". Is that fully black or does it look similar to this:
If the image is not fully black, you can change what you see in the viewport by pressing "z" and switch to "Material Preview"
Please note, that simple geometries such as cubes, spheres etc. are notoriously hard for this addon. It produces much better results when the model is a bit more complex.
I have encountered the same issue now for the first time as well. I will continue to look into this and report back if it's fixable from the add-ons side
Hi!
Blender 4.2
I've installed everything by provided tutorial, models installed, plugin seems to be working.
Problem is that outputs are just black. First time i ran this plugin i've got this:
Next time its just this:
These are the settings:

P.S. I would love to use custom checkpoints and CNet models to adjust art style
We would need more controls for this - steps, cfg scale, etc.
The text was updated successfully, but these errors were encountered: