VAE HERE: https://civarchive.com/models/146075
"SD-XL Inpainting 0.1 is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input, with the extra capability of inpainting the pictures by using a mask.
The SD-XL Inpainting 0.1 was initialized with the stable-diffusion-xl-base-1.0 weights. The model is trained for 40k steps at resolution 1024x1024 and 5% dropping of the text-conditioning to improve classifier-free classifier-free guidance sampling. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and, in 25% mask everything."
Guide for CompfyUI: https://mybyways.com/blog/using-the-sdxl-inpainting-01-model
source: https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1
Description
FAQ
Comments (7)
Not working in A1111, error about the tensor with all nans. SDXL1.0 and SDXL1.0 refiner both working normally.
RTX3070Ti Laptop.
Patiently waiting for this to be made to work in Automatic1111 for the other 70% of us who don't use the spaghetti network.
The file is 4.78GB (uploaded yesterday) and the file on Hugging Face is 5.14GB (uploaded 16 days ago), should I put the 4.78GB file in the "unet" folder instead of downloading the 5.14G version from Hugging Face?
does this will work using CPU ?
Reupload guide for comfy, please! U will save my life!
I wonder if it's possible to train lora specifically for this inpaint model. I tried it with normal lora, but it don't work well together.
its HALF precision ... it runs out of mem with 16GB Vram 4060RTX ^^
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.