No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from lodestones/Chroma1-Base
All models by lodestones →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.
A massive thank you to our supporters who make this project possible.
diffusers Libraryinstall the requirements
pip install transformers diffusers sentencepiece accelerate
ComfyUI For advanced users and customized workflows, you can use Chroma with ComfyUI.
Requirements:
Setup:
T5_xxl model in your ComfyUI/models/clip folder.FLUX VAE in your ComfyUI/models/vae folder.Chroma checkpoint in your ComfyUI/models/diffusion_models folder.Chroma is intended to be used as a base model for researchers and developers to build upon. It is ideal for:
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.
(For a full breakdown, tech report soon-ish.)
<pad> tokens.-x^2) to prevent loss spikes and ensure the model trains effectively on both high-noise and low-noise regions.Chroma1-Base is Chroma-v.48
import torchfrom diffusers import ChromaPipeline
pipe = ChromaPipeline.from_pretrained("lodestones/Chroma1-Base", torch_dtype=torch.bfloat16)pipe.enable_model_cpu_offload()
prompt = [ "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."]negative_prompt = ["low quality, ugly, unfinished, out of focus, deformed, disfigure, blurry, smudged, restricted palette, flat colors"]
image = pipe( prompt=prompt, negative_prompt=negative_prompt, generator=torch.Generator("cpu").manual_seed(433), num_inference_steps=40, guidance_scale=3.0, num_images_per_prompt=1,).images[0]image.save("chroma.png")@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}},}