Pinned

1. YetAnotherStableDiffusion YetAnotherStableDiffusion Public

   StableDiffusion scripts based on huggingface diffusers.

   Python 13 6

2. UMAP maps of internal CLIP text repr... UMAP maps of internal CLIP text representations (direct viewable links)

   1

   ## UMAP maps of internal OpenCLIP ViT-H/14 text representations. Colors are derived from k_means clustering on the unprocessed (1024-dimensional) CLIP feature tensors.

   2

   3

   This variant of CLIP is used in StableDiffusion version 2.x. (https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K)

   4

   ##

   5

   "by \<artist\>":

3. VQGAN-CLIP VQGAN-CLIP Public

   Forked from nerdyrodent/VQGAN-CLIP

   Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

   Python 1

4. glide-text2im glide-text2im Public

   Forked from nerdyrodent/glide-text2im

   GLIDE: a diffusion-based text-conditional image synthesis model. Now with example files for local running.

   Python

5. SwinIR SwinIR Public

   Forked from JingyunLiang/SwinIR

   SwinIR with local processing script

   Python

6. Convert original Stable Diffusion ch... Convert original Stable Diffusion checkpoints and safetensors to diffusers

   1

   # Stable Diffusion model conversion script

   2

   ## Convert from the 'original implementation' to Huggingface diffusers. Both .safetensors and .ckpt checkpoints are supported.

   3

   The script is adapted from the diffusers conversion script: https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py

   4

   5

   **Usage:**