Chroma1-Base is an 8.9B parameter text-to-image foundational model based on FLUX.1-schnell. It is fully Apache 2.0 licensed, ensuring that anyone can use, modify, and build upon it.
As a base model, Chroma1 is intentionally designed to be an excellent starting point for finetuning. It provides a strong, neutral foundation for developers, researchers, and artists to create specialized models.
for the fast CFG "baked" version please go to Chroma1-Flash.
Key Features
High-Performance Base: 8.9B parameters, built on the powerful FLUX.1 architecture.
Easily Finetunable: Designed as an ideal checkpoint for creating custom, specialized models.
Community-Driven & Open-Source: Fully transparent with an Apache 2.0 license, and training history.
Flexible by Design: Provides a flexible foundation for a wide range of generative tasks.
Special Thanks
A massive thank you to our 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. You can try Chroma on their platform:
1import torch
2from diffusers import ChromaPipeline
34pipe = ChromaPipeline.from_pretrained("lodestones/Chroma1-Base", torch_dtype=torch.bfloat16)5pipe.enable_model_cpu_offload()67prompt =[8"A high-fashion close-up portrait of a blonde woman in clear sunglasses. The image uses a bold teal and red color split for dramatic lighting. The background is a simple teal-green. The photo is sharp and well-composed, and is designed for viewing with anaglyph 3D glasses for optimal effect. It looks professionally done."9]10negative_prompt =["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"]1112image = pipe(13 prompt=prompt,14 negative_prompt=negative_prompt,15 generator=torch.Generator("cpu").manual_seed(433),16 num_inference_steps=40,17 guidance_scale=3.0,18 num_images_per_prompt=1,19).images[0]20image.save("chroma.png")
ComfyUI
For advanced users and customized workflows, you can use Chroma with ComfyUI.
Place the T5_xxl model in your ComfyUI/models/clip folder.
Place the FLUX VAE in your ComfyUI/models/vae folder.
Place the Chroma checkpoint in your ComfyUI/models/diffusion_models folder.
Load the Chroma workflow file into ComfyUI and run.
Model Details
Architecture: Based on the 8.9B parameter FLUX.1-schnell model.
Training Data: Trained on a 5M sample dataset curated from a 20M pool, including artistic, photographic, and niche styles.
Technical Report: A comprehensive technical paper detailing the architectural modifications and training process is forthcoming.
Intended Use
Chroma is intended to be used as a base model for researchers and developers to build upon. It is ideal for:
Finetuning on specific styles, concepts, or characters.
Research into generative model behavior, alignment, and safety.
As a foundational component in larger AI systems.
Limitations and Bias Statement
Chroma is trained on a broad, filtered dataset from the internet. As such, it may reflect the biases and stereotypes present in its training data. The model is released in a state as is and has not been aligned with a specific safety filter.
Users are responsible for their own use of this model. It has the potential to generate content that may be considered harmful, explicit, or offensive. I encourage developers to implement appropriate safeguards and ethical considerations in their downstream applications.
Summary of Architectural Modifications
(For a full breakdown, tech report soon-ish.)
12B → 8.9B Parameters:
TL;DR: I replaced a 3.3B parameter timestep-encoding layer with a more efficient 250M parameter FFN, as the original was vastly oversized for its task.
MMDiT Masking:
TL;DR: Masking T5 padding tokens enhanced fidelity and increased training stability by preventing the model from focusing on irrelevant <pad> tokens.
Custom Timestep Distributions:
TL;DR: I implemented a custom timestep sampling distribution (-x^2) to prevent loss spikes and ensure the model trains effectively on both high-noise and low-noise regions.
P.S
Chroma1-Base is Chroma-v.48
Citation
@misc{rock2025chroma,
author = {Lodestone Rock},
title = {Chroma1-Base},
year = {2025},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/lodestones/Chroma1-Base}},
}
