models/Chroma - v.35

Chroma - v.35

11/11/2025

11:26:46 PM

Related Keywords & Tags

base model,base_model,base stable diffusion model,checkpoint,chroma,chroma1-base,chroma1-flash,chroma1-hd,chroma1-radiance,fine-tuning,lodestone,open-source foundational model,v.35

A blue-tinted digital painting of a grotesque pale-skinned creature with elongated ears and sharp teeth hanging and emerging from a rocky cave ceiling, dripping saliva.

A detailed mutant fish with glowing orange eyes and bioluminescent features looming in a dark, eerie, contaminated environment with nuclear bio hazard waste.

Silhouettes of people walking in a neon-lit cityscape with colorful gray tones and vibrant vertical light streaks in pink, orange, and blue.

Close-up of a menacing demon with glowing red eyes and sharp teeth, exhaling fire and steam while gripping an ornate dagger engraved with fiery patterns.

Close-up of a cinematic, detailed eye with fiery orange iris amidst a dynamic, rainy storm 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

cfg

4.5

resolution

512x512, 1024x1024

Creator Sponsors

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

Alternative option: FP8 Scaled Quant (Format used by ComfyUI with possible inference speed increase)
Alternative option: GGUF Quantized (You will need to install ComfyUI-GGUF custom node)

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.