These are ControlNet weights trained on stabilityai/stable-diffusion-xl-base-1.0 for PBR material generation from height maps. The model generates a 4-channel output, corresponding to a 3-channel BaseColor map and a 1-channel Roughness map. You can find some example images below. For each prompt, the grid shows the input height map, followed by the generated BaseColor map(s) and then the generated Roughness map(s).

Prompt: a photorealistic, highly detailed photograph of a lunar surface material

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]