Model Card (SVDQuant)

Language: English | 中文

Model name

• Model repo: tonera/Chroma1-HD-SVDQ
• Base (Diffusers weights path): tonera/Chroma1-HD-SVDQ (repo root)
• Quantized Transformer weights: tonera/Chroma1-HD-SVDQ/svdq-<precision>_r32-Chroma1-HD.safetensors

Quantization / inference tech

• Inference engine: vitoom-nunchaku — community-maintained Nunchaku build with Chroma support

Nunchaku is a high-performance inference engine for 4-bit (FP4/INT4) low-bit neural networks. It implements SVDQuant and related optimizations. The Chroma1-HD quantized weights in this repository are meant to be used with vitoom-nunchaku on supported GPUs.

Upstream Nunchaku has not merged Chroma support for a long time (PR #928 still pending). Do not copy transformer_chroma.py manually.

Install vitoom-nunchaku (Option 1: manual Python environment)

Install the prebuilt wheel from tonera/vitoom-nunchaku that matches your platform, Python, and CUDA:

pip install torch==2.11.* torchvision==0.26.* torchaudio==2.11.* \
  --index-url https://download.pytorch.org/whl/cu130

hf download tonera/vitoom-nunchaku \
  nunchaku-1.3.0.dev20260622+cu13.0torch2.11-cp311-cp311-linux_x86_64.whl \
  --local-dir ./wheels

pip install ./wheels/nunchaku-1.3.0.dev20260622+cu13.0torch2.11-cp311-cp311-linux_x86_64.whl

For cu128, cp310, or ARM64 aarch64 wheels, see the vitoom-nunchaku README.

Verify:

python -c "import nunchaku; from nunchaku import NunchakuChromaTransformer2dModel; print(nunchaku.__version__)"

Usage example (Diffusers + Nunchaku Transformer)

Assumes vitoom-nunchaku is installed:

import torch
from diffusers import ChromaPipeline

from nunchaku import NunchakuChromaTransformer2dModel
from nunchaku.utils import get_precision

MODEL = "Chroma1-HD-SVDQ"
REPO_ID = f"tonera/{MODEL}"

if __name__ == "__main__":
    transformer = NunchakuChromaTransformer2dModel.from_pretrained(
        f"{REPO_ID}/svdq-{get_precision()}_r32-{MODEL}.safetensors"
    )

    pipe = ChromaPipeline.from_pretrained(
        f"{REPO_ID}",
        transformer=transformer,
        torch_dtype=torch.bfloat16,
        use_safetensors=True,
    ).to("cuda")

    prompt = "Make Pikachu hold a sign that says 'Nunchaku is awesome', yarn art style, detailed, vibrant colors"
    image = pipe(prompt=prompt, guidance_scale=2.5, num_inference_steps=40).images[0]
    image.save("Chroma1.png")

Option 2 (recommended: vitoom)

For a ready-to-use Web UI without manual wheel install, deploy vitoom. Its visual module includes vitoom-nunchaku with Chroma support. See docker-usage-en.md.

git clone https://github.com/tonera/vitoom.git
cd vitoom
python scripts/setup_vitoom.py
python scripts/load_vitoom_images.py --components backend,visual
docker compose up -d backend
docker compose -f docker-compose.inference.release.yml --profile visual up -d

In the Web UI: Models → download and activate tonera/Chroma1-HD-SVDQ → run in Image workspace.