Diffus
Começar
modelos/Chroma - v.30

Chroma - v.30

Lodestone
|
12/16/2025
|
11:23:14 PM
| Discussion|
0
Dark menacing humanoid robot with a heavily rusted and damaged exterior, glowing orange-red teeth under a hooded helmet in a smoky dark gray background.
Digital painting of a ghostly woman in a flowing tattered white dress wearing a crown of dark twisted flowers, set against a dark, textured, abstract background.

Prompts Recomendados

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.30 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.

Prompts Negativos Recomendados

low quality, ugly, unfinished, out of focus

Parâmetros Recomendados

samplers

Euler

steps

16

cfg

4

Dicas

Chroma is fully uncensored, reintroducing missing anatomical concepts for more complete image generation.

The model is still training and open to community feedback to improve quality and performance.

Quantization options include FP8 Scaled Quant for inference speed and GGUF Quantized for ComfyUI-GGUF custom node compatibility.

Patrocinadores do Criador

Fictional.ai

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

Support community-driven AI at https://ko-fi.com/lodestonerock/goal?g=1. Every bit helps!

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

Anterior
Krysdecker_style - Krysdeker_ILL+Pony V2
Próximo
Masked - v1.0
Usar este modelo

Detalhes do Modelo

Tipo de modelo

Checkpoint

Modelo base

Chroma

Versão do modelo

v.30

Hash do modelo

efd9dd67be

Criador

Lodestone's avatar
Lodestone

Discussão

Por favor, faça log in para deixar um comentário.

Imagens por Chroma - v.30

Dark menacing humanoid robot with a heavily rusted and damaged exterior, glowing orange-red teeth under a hooded helmet in a smoky dark gray background.
Digital painting of a ghostly woman in a flowing tattered white dress wearing a crown of dark twisted flowers, set against a dark, textured, abstract background.

Imagens com base model

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

Imagens com chroma

A powerful flaming tiger roaring with intensity, surrounded by vibrant blue and orange flames, created using stable diffusion AI technology.
A highly detailed, AI generated dark fantasy image of a ferocious werewolf roaring under a stormy night sky, using Stable Diffusion.