PnPInversion
PnPInversion copied to clipboard
cure-lab
[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"
When I try to edit one image with the method pixel2pixel-zero on RTX3090, 24G, It reports: ``` editing image [scripts/0_right.jpg] with [directinversion+pix2pix-zero] 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 50/50 [00:16> allocated memory try setting max_split_size_mb...
Dear PnPInversion authors, Thank you for sharing this great work. I am trying to use PIE-Bench for evaluation. There are image masks in the dataset; are we allowed to use...
Key error: "down_cross". Here are some key errors, which seems like the attention store is wrong.
想请教下作者，直接存储prompt_src在inversion过程中每一步的latent而不是loss，然后直接用于sampling过程的非编辑区域，相当于非编辑区域用prompt_src部分的latent，编辑区域用prompt_tgt的latent，写法是不是和原来是等价的？
Hi I'm a beginner. When I used the model in run_editing_p2p.py with the method directinversion+p2p,OSError error occured，which is OSError:CompVis/stable-diffusion-v1-4 does not appear to have a file named model_index.json. I have...
Hello PNPinversion team, thank you for your wonderful works and your contribution for making these codes public, as well as the dataset. I am now using your evaluation framework and...
Hello, Thank you for your excellent project. However, I have a question. When I ran the experiment, I noticed that some evaluation metrics returned NaN values in cases like the...
Thanks for your excellent work, and I am trying to work on this demo. But when I've configured the environment and run "python run_editing_p2p.py --output_path output --edit_category_list 0 --edit_method_list. When...
Dear authors, Excellent work! I found it very useful. I want some clarification on some details. Looks like the distance on the target branch never being used. Why did we...
