Paint3D icon indicating copy to clipboard operation
Paint3D copied to clipboard

Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model

Results 21 Paint3D issues
Sort by recently updated
recently updated
newest added

In the new version, it will appear whether I execute t2t or t2i. AttributeError: 'StableDiffusionControlNetPipeline' object has no attribute 'load_ip_adapter'

Thank you for open sourcing this great work ! Is there a plan to release the training code for uv-position control net ? Releasing this would help a lot with...

When generating textures for architectural mesh models with the prompt texts "residential_building, red bricks facade, wooden roof," the resulting textures exhibit inconsistency between adjacent viewpoints. For instance, the roof texture...

Hi, thanks for your great work. I put my obj file on stage 1 like this: python pipeline_paint3d_stage1.py --sd_config controlnet/config/depth_based_inpaint_template.yaml --render_config paint3d/config/train_config_paint3d.py --mesh_path /public/omniteam/yejr/Paint3D-main/input_data/penguin/face_blue.obj --outdir outputs/penguin/stage1 And I get the...

Do you plan to release multi-gpu support?

Why, after replacing it with my own untextured human model, does the generated mesh.obj not look like a human model but rather like a block of stone? Are there any...

is that using https://huggingface.co/datasets/allenai/objaverse as training data? can you show me some demo train data, i would like to use your framework to create building texture

This is a fresh install. I tried generating the coarse texture by running: `python pipeline_paint3d_stage1.py --sd_config controlnet/config/depth_based_inpaint_template.yaml --render_config paint3d/config/train_config_paint3d.py --mesh_path demo/objs/Suzanne_monkey/Suzanne_monkey.obj --prompt " " --ip_adapter_image_path demo/objs/Suzanne_monkey/img_prompt.png --outdir outputs/img_stage1` This resulted...

Hi, I try to use paint3d on my own mesh and I get the folling error: ![image](https://github.com/user-attachments/assets/4e458ad2-a994-494e-b99e-aca137486c88) Seems like the the uv faces index doesn't match the number of faces:...

Hi, Thanks again for open-sourcing this awesome work. I found that the UV diffusion models are sensitive to UV quality. If there are discontinuous parts in the UV, there will...