modele/Chroma - v.41-low-step-rl

Chroma - v.41-low-step-rl

|
8/16/2025
|
3:30:46 AM
| Discussion

Zalecane podpowiedzi

Extreme close-up photograph of a single tiger eye, direct frontal view. The iris is very detailed and the pupil resembling a dark void. The word "CHROMA LOW STEPS RL TRAINING" is across the lower portion of the image in large white stylized letters, with brush strokes. Each strand of the thick fur is highly detailed and distinguishable. Natural lighting to capture authentic eye shine and depth.

Zalecane negatywne podpowiedzi

low quality, ugly, unfinished, out of focus

Zalecane parametry

samplers

DPM++ 2M

steps

14

cfg

1.3

Wskazówki

Model training is ongoing, and user feedback is encouraged.

Use the latest model from the Hugging Face repo https://huggingface.co/lodestones/Chroma

Alternative quantization options are available including FP8 Scaled Quant and GGUF Quantized formats.

You can follow live training progress via https://training.lodestone-rock.com/

ComfyUI inference and workflow resources are provided to facilitate integration.

Sponsorzy twórcy

Fictional.ai Support

Shoutout to Fictional.ai for the awesome support — seriously appreciate you helping push open-source AI forward.

Hey everyone!

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

Quantization options

Special Thanks

Shoutout to Fictional.ai for the awesome support — seriously appreciate you helping push open-source AI forward.

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

my discord: discord.gg/SQVcWVbqKx

Poprzedni
Cyberpunk Anime Style - SDXL v2.0 light version
Następny
Hyperdetailed Illustration - SDXL

Szczegóły modelu

Typ modelu

Checkpoint

Model bazowy

Other

Wersja modelu

v.41-low-step-rl

Hash modelu

f6fa0d119e

Twórca

Dyskusja

Proszę się log in, aby dodać komentarz.