loboere

even deleting that part nothing happens !python inverse_render_double_semantic.py exp_name /content/FENeRF/wo_latent_grid/200000_generator.pth --image_path data/examples/image.jpg --seg_path data/examples/mask.png --background_mask --image_size 128 --latent_normalize --lambda_seg 1. --lambda_img 0.2 --lambda_percept 1. --lock_view_dependence True --recon

!python demo.py --in_img /content/9.jpg --in_audio /content/acapella_res.wav --output_path /content/out

for now implement the function of using a part of a real image you can try it in the colab that is in my repository https://github.com/loboere/latent-diffusion-inpainting-colab

hi @clumsynope, can you tell me how to run the cross-identity? are you using a custom image?

how use custom images instead `video_item['video_name']`

same :(

official code here []https://github.com/google/prompt-to-prompt

please release sd1.5

can someone add the inpainting option in the dreambooth colab here https://github.com/huggingface/diffusers/blob/acd317810bc138b3a78fa30e1b3da1006c1d60ad/docs/source/training/overview.mdx https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb

can you please adapt this to this colab https://github.com/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb ,this colab trains based only on the name of the images, without class images and that complicated stuff