Diffus
Get started
models/Chroma - v.41-low-step-rl

Chroma - v.41-low-step-rl

Lodestone
|
7/27/2025
|
3:32:12 AM
| Discussion|
0
A portrait of a young woman with long white hair and blue eyes wearing a futuristic black corset dress resembling a skeleton, depicted in an abstract, gestural brushstroke style with muted tones.
A serene young girl with short ashy-gray hair leans against a detailed cream-white mechanical android adorned with purple flowers, set against a muted cool-toned background.
A dark, solitary female silhouette stands amidst a vibrant, abstract urban cityscape with swirling colors, textured brushstrokes, and glowing street lamps.
A young fair-skinned woman with flowing blonde hair and pale blue eyes sits among ancient ruins adorned with serpentine sculptures, surrounded by yellow daffodils and glowing soft ethereal light.
Digital illustration of a tall, intricate futuristic building made of metal and glass with wires, set in a barren desert under a deep blue sky with clouds.
Minimalist painting featuring a poised woman’s graceful back, created with bold, textured abstract brushstrokes in muted blue, grey, pink, and white tones.
A majestic castle with classical columns and arches nestled in a mountainous landscape under a starry sky, illuminated by cool and warm lighting.
Oil painting of a medieval castle on a hill with dark stone walls and turrets, a winding path with horse riders, a village, and a cloudy sky with soft, dramatic light.
A watercolor portrait of a virtual teenage idol with pastel pink bob hair, wearing a semi-transparent orange dress decorated with gold leaf, set against an abstract blue and brick textured background.
Close-up of a faceless cyborg with a cracked, translucent orb face, glowing neon orange veins on matte black and white ceremonial armor, set against a stormy, abstract background with swirling shapes and crimson red highlights.
Cyberpunk girl with white braided hair, black horns, and red eyes wearing a kimono, seated against a dark, abstract red and black painted background.
Detailed portrait of a cyborg girl with pink hair and mechanical joints, painted in a cyberpunk, abstract realism style with textured brushstrokes.

Recommended Prompts

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.

Recommended Negative Prompts

low quality, ugly, unfinished, out of focus

Recommended Parameters

samplers

DPM++ 2M

steps

14

cfg

1.3

Tips

The model is still training; community feedback is encouraged.

Quantization options available: FP8 Scaled Quant (for faster inference with ComfyUI) and GGUF Quantized (requires ComfyUI-GGUF node).

Support the ongoing training of this open-source model via Ko-fi or ETH donations.

Creator Sponsors

Fictional.ai

Shoutout to Fictional.ai for the awesome support — seriously appreciate 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

Previous
Amazing Embeddings - fcNegative + fcPortrait suite - fcNeg
Next
All Disney Princess XL LoRA Model from Ralph Breaks the Internet - Illustrious
Use this model

Model Details

Model type

Checkpoint

Base model

Other

Model version

v.41-low-step-rl

Model hash

f6fa0d119e

Creator

Lodestone's avatar
Lodestone

Discussion

Please log in to leave a comment.

Images by Chroma - v.41-low-step-rl

base model Images

chroma Images