For this model the only one available contol input is the conditioning_image from dataset irodkin/celeba_with_llava_shorter_captions

And this image the model actually ignores. Its just experimental text2image

Downloads last month
4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train irodkin/controlnet_celeba_with_llava_captions_ft