Chroma by Lodestone, quantized using GGUF by silveroxides and Clybius.
Original description:
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.
The model is still training right now, and I’d love to hear your thoughts! Your input and feedback are really appreciated.
What Chroma Aims to Do
Training on a 5M dataset, curated from 20M samples including anime, furry, artistic stuff, and photos.
Fully uncensored, reintroducing missing anatomical concepts.
Built as a reliable open-source option for those who need it.
See the Progress
Hugging Face Repo: https://huggingface.co/lodestones/Chroma
Hugging Face Debug Repo: https://huggingface.co/lodestones/chroma-debug-development-only
Live WandB Training Logs: https://wandb.ai/lodestone-rock/optimal%20transport%20unlocked
ComfyUI Inference node [WIP]: https://github.com/lodestone-rock/flux-mod
ComfyUI workflow: https://huggingface.co/lodestones/Chroma/resolve/main/simple_workflow.json
Training code!: https://github.com/lodestone-rock/flow
Support Open-Source AI
The current pretraining run has already used 5000+ H100 hours, and keeping this going long-term is expensive.
If you believe in accessible, community-driven AI, any support would be greatly appreciated.
👉 [https://ko-fi.com/lodestonerock/goal?g=1] — Every bit helps!
ETH: 0x679C0C419E949d8f3515a255cE675A1c4D92A3d7
their discord: discord.gg/SQVcWVbqKx
Description
scaled fp8, requires the testing branch of fluxmod
FAQ
Comments (5)
Comfy merged in Chroma support. Now workflows shouldn't need anything extra installed
let's go! i hope teacache and torch compile will start working
did a bit of testing as of now, the comfy implementation seems to be giving very different results compared to fluxmod, i'm somewhat unsure as to what the optimal workflow for it would be, as it often produces more artifacts and generally worse results
I let the team know. Hopefully they'll be able to find what changed with the PR update when it got merged.
figured out the issue, you have to add the ModelSamplingFlux node