models/Chroma1-HD-GGUF-&-FP8 - Q8_0

Chroma1-HD-GGUF-&-FP8 - Q8_0

10/18/2025

5:36:38 PM

Related Keywords & Tags

base model,checkpoint,chroma,chroma1,chroma1-base,chroma1-hd,chroma1-hd-gguf-&-fp8,fp8,gguf,high resolution image generation,open-source foundational model,q8_0,quant,quantized,s1lv3rc01n,stable diffusion

An oil painting of a futuristic street warrior with spiked blue hair wearing an oversized jacket and massive mechanical gauntlets against a solid purple background in thick brushstrokes.

Recommended Prompts

This is a nature documentary close-up photograph of the right side of the face of a tiger. The photograph is centered on it's highly detailed and speckled eye surrounded by intricately detailed fur. Overlaid at the center of the image is a title text that says "CHROMA1-HD" in a large white 3D letters. Amateur photography. Unfiltered. Real life. Natural light. Subtle shadows., Overlaid at the center of the image, in a large bold font, is the text "Chroma1-HD". This is a nature documentary photograph of an extreme close-up of a tiger face with focus on it's eye. Amateur photograph. Unfiltered. Real life. Natural light. Subtle shadows.

Recommended Negative Prompts

This low quality greyscale unfinished sketch is inaccurate and flawed. The image is very blurred and lacks detail with excessive chromatic aberrations and artifacts. The image is overly saturated with excessive bloom. It has a toony aesthetic with bold outlines and flat colors., This greyscale unfinished sketch has bad proportions, is featureless and disfigured. It is a blurry ugly mess and with excessive gaussian blur. low quality. ugly. unfinished. bad composition.

Recommended Parameters

samplers

Euler

steps

26 - 32

cfg

3.2 - 3.5

resolution

512x512, 1024x1024

Tips

Chroma1-Base is suitable if planning long fine-tuning cycles with high-res training at the final epochs for faster convergence.

Chroma1-HD is ideal for quick fine-tuning or LoRA applications at high resolution.

Chroma1-Flash delta weights can be applied to any Chroma version to increase inference speed; adjust strength accordingly.

Creator Sponsors

This is the official model page for

Chroma1-HD GGUF Quants

Workflow is in the training data .zip file

The following is a copy of original model page.

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.