Get Chroma ! [GGUF/FP8/BF16] (Uncensored Schnell Finetune)

Chroma is a new Finetune based on Flux Schnell, it claims to be uncensored and is available in several weight formats: (workflows at the bottom)

Chroma is a 8.9B parameter model based on FLUX.1-schnell (technical report coming soon!). It’s fully Apache 2.0 licensed, ensuring that anyone can use, modify, and build on top of it—no corporate gatekeeping. (authors note)

Official: https://huggingface.co/lodestones/Chroma
FP8: https://huggingface.co/Clybius/Chroma-fp8-scaled
GGUF: https://huggingface.co/silveroxides/Chroma-GGUF

You will need:

GGUF WEIGHTS
Q4_0 (5.43GB) https://huggingface.co/silveroxides/Chroma-GGUF/resolve/main/chroma-unlocked-v30/chroma-unlocked-v30-Q4_0.gguf
Q8_0 (9.47GB) https://huggingface.co/silveroxides/Chroma-GGUF/resolve/main/chroma-unlocked-v30/chroma-unlocked-v30-Q8_0.gguf
place inside: ComfyUI/models/diffusion_models

use the same CLIP/VAE as used with Flux DEV or SCHNELL models

GGUF CLIP
Q8_0 (5.06GB) https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/resolve/main/t5-v1_1-xxl-encoder-Q8_0.gguf
place inside: ComfyUI/models/clip

Workflows:

txt2img

img2img