stable-diffusion
stable-diffusion copied to clipboard
runwayml
Latent Text-to-Image Diffusion
Runway Inpainting in colab and HuggingFace works worse than on the site. During generation, the entire picture is distorted, even the area that was not selected. This leads to deformation...
Thank you for open-sourcing your code and pre-training model. I maintain an inpainting tool [Lama Cleaner](https://github.com/Sanster/lama-cleaner) that allows anyone to easily use the SOTA inpainting model. https://user-images.githubusercontent.com/3998421/196976498-ba1ad3ab-fa18-4c55-965f-5c6683141375.mp4 It's really easy...
v1-1-to-v1-5.png currently has a transparent background which means one can not read the text on Github dark theme
Adds MPS device support to run Runway inpainting on M1/M2 Macbooks. _environment-mac.yaml_ gets rid of CUDA related setup, sets up a Conda environment for Mac. Note: Needs `export PYTORCH_ENABLE_MPS_FALLBACK=1` because...
Runway Inpainting in colab and HuggingFace works worse than on the site. During generation, the entire picture is distorted, even the area that was not selected. This leads to deformation...
venv "D:\AIG\stable-diffusion-webui\venv\Scripts\Python.exe" Python 3.11.0 (main, Oct 24 2022, 18:26:48) [MSC v.1933 64 bit (AMD64)] Commit hash: 737eb28faca8be2bb996ee0930ec77d1f7ebd939 Installing torch and torchvision Traceback (most recent call last): File "D:\AIG\stable-diffusion-webui\launch.py", line 205,...
I am busy porting the inpainting functionality into the InvokeAI distribution. One question that I have is whether the inpainting model can also be used for pure `txt2img` or `img2img`....
How to finetune inpainting model on custom dataset?
Hi! Most of the SD checkpoints mention "dropping of the text-conditioning to improve classifier-free guidance sampling." However, I couldn't find the config parameter that does this nor the code that...
