---
pipeline_tag: text-to-image
library_name: diffusers
tags:
  - Chroma
  - quantization
  - svdquant
  - nunchaku
  - fp4
  - int4
base_model: tonera/Chroma1-HD-SVDQ
base_model_relation: quantized
license: apache-2.0
---

# Model Card (SVDQuant)

> **Language**: English | [中文](README_CN.md)

![Chroma1-HD](chroma1-hd.png)


## 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](https://huggingface.co/tonera/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](https://github.com/nunchaku-ai/nunchaku) has not merged Chroma support for a long time ([PR #928](https://github.com/nunchaku-ai/nunchaku/pull/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](https://huggingface.co/tonera/vitoom-nunchaku)** that matches your platform, Python, and CUDA:

```bash
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](https://huggingface.co/tonera/vitoom-nunchaku).

Verify:

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

## Usage example (Diffusers + Nunchaku Transformer)

Assumes **vitoom-nunchaku** is installed:

```python
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](https://github.com/tonera/vitoom). Its **visual** module includes **vitoom-nunchaku** with Chroma support. See [docker-usage-en.md](https://github.com/tonera/vitoom/blob/main/docker-usage-en.md).

```bash
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.