Stable Diffusion Sketch, an Android client app that connect to your own ComfyUI or A1111-sd-webui

An open source community implementation of the model from the paper: "Movie Gen: A Cast of Media Foundation Models". Join our community to help implement this model!

Run Stable diffusion 3 on low VRAM systems

Cog template for Stable Diffusion 3 (ComfyUI implementation)

A TF2.0 implementation of RL baselines.

SD3 with more output variety

Shuffle LLama-3.2 layers and have it prompt an image. Node works with any model - Flux, SD3, SDXL...

100+ billion unique prompt. Create random prompts to help with learning better prompting techniques. Works with any AI platform!

Shuffle GPT-2's layers and have it prompt an image. Node works with any model - Flux, SD3, SDXL...

run flux1/sd3 model with beginner GPU (low cost) or even CPU

Heuristic modification of the Heun sampler using normalized distances.

WIP Google Colab Notebook for ComfyUI with Google Drive and Stable Diffusion v3 support.

stable-diffusion-3-medium with gradio and T5 long token