A digital painting depicting a desolate orange desert landscape under a fiery glowing sun with three cloaked figures walking away from the viewer towards dark crumbling ruins.
A mystical forest scene featuring a moss-covered thatched roof cottage and a yelling old hag visible at the porch, with a large gnarled tree and white wildflowers in the foreground, and a conical stone tower partially obscured by mist in the background.
A towering monolithic horror figure cloaked in shadow, looming over an icy Antarctic landscape under a dark, cloudy sky.
A cat in a dimly lit prison-like room facing left, featuring a detailed tattoo of a black and blue yarn ball with a halo and cross on its right side, wearing a bandana and nose ring piercing.
A towering dark figure with horns playing a lute amid a stormy, blood-raining sky over a sprawling cityscape with glowing red cracks below.
A dark, shadowy demon with prominent horns, a screaming skull-like face with black tears, and sharp claws, emerging from darkness in a gothic horror style.
Dark-skinned cyberpunk demon with fiery orange and black scales, glowing blue cybernetic eyes, wearing a tattered white hooded jacket, orange scarf, and holding a large glowing fiery axe
A surreal portrayal of a person's face held by two hands, with one side showing a cracked skull and the other a distressed expression, all in dark, muted tones.
Dark cloaked figure surrounded by yellowish walls filled with multiple holes, each hole containing an eye with long lashes.
Silhouette of a wolf sitting on hills at night, gazing at a large bright moon surrounded by stars and colorful sunset sky.
Digital painting of a disgruntled tiger with orange and white fur partially covered in snow, surrounded by lush green and colorful spring foliage under unusual weather conditions.
Digital painting of a Border Collie with dark brown and black fur, white face, and piercing blue eyes grinning with head tilted back against a dark brown background.

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 V.35 now with less steps" is across the lower portion of the image in large white stylized letters, with brush strokes resembling those made with Japanese calligraphy. 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

Euler

steps

16

cfg

4.5

Tips

Chroma offers alternative quantization options including FP8 Scaled Quant (useful for inference speed with ComfyUI) and GGUF Quantized format (requires ComfyUI-GGUF custom node).

The model is still training, so community feedback is highly encouraged.

Support for ongoing training of open-source AI models can be done via Ko-fi or Ethereum donations.

Creator Sponsors

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

Previous
Realistic Vision V6.0 B1 - V5.1 (VAE)
Next
Stable Diffusion 3.5 Large - Large

Model Details

Model type

Checkpoint

Base model

Other

Model version

v.35-detail-calibrated

Model hash

e01d54637f

Creator

Discussion

Please log in to leave a comment.