Primarily for use in ComfyUI, but is open for all that works in CompVis based format.

These are pruned, safetensor variants DynamiCrafter models only containing the necessary UNet, as well as the Image Projection Model.

In order to use the text encoder, please download the accompanying models.

SD 2.1 Open CLIP: https://huggingface.co/stabilityai/stable-diffusion-2-1/resolve/main/text_encoder/model.safetensors?download=true

VAE: https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors?download=true

ClipVision: https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/resolve/main/open_clip_pytorch_model.safetensors?download=true

---
license: apache-2.0
---