Diffus
Get started
models/Chroma - v1.0-HD

Chroma - v1.0-HD

Lodestone
|
9/3/2025
|
11:21:09 PM
| Discussion
Painting of a black and white cat sitting in a grassy field with eyes closed, textured brushstrokes emphasizing soft fur and a calm, serene mood.
A dark, mysterious male silhouette surrounded by swirling ethereal mist and glowing lanterns in a warm-toned fantasy realm rendered with oil painting style.
Mystical serpentine creature with shimmering iridescent scales emerging from mist in front of an ancient Egyptian temple adorned with hieroglyphics.
Close-up of a woman's face crafted from woven frayed denim threads and embroidered silk patches in burnt sienna and cobalt blue, with goldenrod stitching forming constellation patterns across her cheeks.
Massive steampunk mechanical structure with dome-shaped top, large round eyes, pipes, gears, and claw-like appendages under a cloudy sky.
A sinister female elf floats weightlessly in an abstract dark painting with glowing white-turquoise eyes and a vivid red exclamation mark in the background.
Foggy cityscape with tall buildings covered in scaffolding lit by neon green and orange light, featuring a small figure standing on a rooftop.
A monochromatic sepia-toned scene with a large cracked circular structure suspended behind a solitary figure standing on a fragile platform.
A man tenderly holds a woman close, their faces illuminated by soft blue neon reflections from a futuristic city skyline in a retro cyberpunk style.
A retro cyberpunk styled man gazing upward with a metallic visor reflecting red and green lights connected to detailed cybernetic implants revealing glowing circuitry beneath his skin.
Hyperdetailed dark demon with glowing red eyes in a red and black color scheme, showcasing an ominous, high contrast surreal atmosphere.
A futuristic armored warrior in a dynamic low-angle pose wearing a metallic horned helmet with glowing red eyes, wielding a glowing blue energy sword amid red and blue energy effects.

Recommended Prompts

Extreme close-up photo of a tiger eye. large title "Chroma1" overlayed in the center of the image

Recommended Negative Prompts

low quality, ugly, unfinished, out of focus

Recommended Parameters

samplers

Heun

steps

13

cfg

1

resolution

512x512, 1024x1024

Tips

Chroma1-Base offers a solid foundation ideal for longer fine-tuning with high-res training at later epochs for faster convergence.

Chroma1-HD is recommended for quick fine-tuning or LoRA on high-resolution 1024x1024 images.

Chroma1-Flash applies delta weights to any Chroma model to speed up inference without GAN-based training; adjust strength accordingly.

Chroma1-Radiance is a work-in-progress pixel space model aimed at eliminating VAE compression artifacts.

Alternative quantized options include FP8 Scaled Quant and GGUF Quantized versions compatible with ComfyUI.

Creator Sponsors

Fictional.ai Advertisement


Hey everyone,

A while back, I posted about Chroma, my work-in-progress, open-source foundational model. I got a ton of great feedback, and I'm excited to announce that the base model training is finally complete, and the whole family of models is now ready for you to use!

A quick refresher on the promise here: these are true base models.

I haven't done any aesthetic tuning or used post-training stuff like DPO. They are raw, powerful, and designed to be the perfect, neutral starting point for you to fine-tune. We did the heavy lifting so you don't have to.

And by heavy lifting, I mean about 105,000 H100 hours of compute. All that GPU time went into packing these models with a massive data distribution, which should make fine-tuning on top of them a breeze.

As promised, everything is fully Apache 2.0 licensed—no gatekeeping.

TL;DR:

Release branch:

  • Chroma1-Base: This is the core 512x512 model. It's a solid, all-around foundation for pretty much any creative project. You might want to use this one if you’re planning to fine-tune it for longer and then only train high res at the end of the epochs to make it converge faster.

  • Chroma1-HD: This is the high-res fine-tune of the Chroma1-Base at a 1024x1024 resolution. If you're looking to do a quick fine-tune or LoRA for high-res, this is your starting point.

Research Branch:

  • Chroma1-Flash: A fine-tuned version of the Chroma1-Base I made to find the best way to make these flow matching models faster. This is technically an experimental result to figure out how to train a fast model without utilizing any GAN-based training. The delta weights can be applied to any Chroma version to make it faster (just make sure to adjust the strength).

  • Chroma1-Radiance [WIP]: A radical tuned version of the Chroma1-Base where the model is now a pixel space model which technically should not suffer from the VAE compression artifacts.

Quantization options

Special Thanks

A massive thank you to the supporters who make this project possible.

  • Anonymous donor whose incredible generosity funded the pretraining run and data collections. Your support has been transformative for open-source AI.

  • Fictional.ai for their fantastic support and for helping push the boundaries of open-source AI.

Support this project!

https://ko-fi.com/lodestonerock/

BTC address: bc1qahn97gm03csxeqs7f4avdwecahdj4mcp9dytnj
ETH address: 0x679C0C419E949d8f3515a255cE675A1c4D92A3d7

my discord: discord.gg/SQVcWVbqKx

Previous
CyberRealistic XL - v5.3
Next
YFG FaceGear [Flux] - v1.0
Use this model

Model Details

Model type

Checkpoint

Base model

Other

Model version

v1.0-HD

Model hash

d446d9695d

Creator

Lodestone's avatar
Lodestone

Discussion

Please log in to leave a comment.

Images by Chroma - v1.0-HD

Painting of a black and white cat sitting in a grassy field with eyes closed, textured brushstrokes emphasizing soft fur and a calm, serene mood.
A dark, mysterious male silhouette surrounded by swirling ethereal mist and glowing lanterns in a warm-toned fantasy realm rendered with oil painting style.
Mystical serpentine creature with shimmering iridescent scales emerging from mist in front of an ancient Egyptian temple adorned with hieroglyphics.
Close-up of a woman's face crafted from woven frayed denim threads and embroidered silk patches in burnt sienna and cobalt blue, with goldenrod stitching forming constellation patterns across her cheeks.
Massive steampunk mechanical structure with dome-shaped top, large round eyes, pipes, gears, and claw-like appendages under a cloudy sky.
A sinister female elf floats weightlessly in an abstract dark painting with glowing white-turquoise eyes and a vivid red exclamation mark in the background.
Foggy cityscape with tall buildings covered in scaffolding lit by neon green and orange light, featuring a small figure standing on a rooftop.
A monochromatic sepia-toned scene with a large cracked circular structure suspended behind a solitary figure standing on a fragile platform.
A man tenderly holds a woman close, their faces illuminated by soft blue neon reflections from a futuristic city skyline in a retro cyberpunk style.
A retro cyberpunk styled man gazing upward with a metallic visor reflecting red and green lights connected to detailed cybernetic implants revealing glowing circuitry beneath his skin.
Hyperdetailed dark demon with glowing red eyes in a red and black color scheme, showcasing an ominous, high contrast surreal atmosphere.
A futuristic armored warrior in a dynamic low-angle pose wearing a metallic horned helmet with glowing red eyes, wielding a glowing blue energy sword amid red and blue energy effects.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

chroma Images

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.