license: other
license_name: flux-1-dev-non-commercial-license
tags:
- text-to-image
- SVDQuant
- FLUX.1-dev
- INT4
- FLUX.1
- Diffusion
- Quantization
language:
- en
base_model:
- black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
datasets:
- mit-han-lab/svdquant-datasets
library_name: diffusers
Quantization Library: DeepCompressor Inference Engine: Nunchaku
SVDQuant is a post-training quantization technique for 4-bit weights and activations that well maintains visual fidelity. On 12B FLUX.1-dev, it achieves 3.6× memory reduction compared to the BF16 model. By eliminating CPU offloading, it offers 8.7× speedup over the 16-bit model when on a 16GB laptop 4090 GPU, 3× faster than the NF4 W4A16 baseline. On PixArt-∑, it demonstrates significantly superior visual quality over other W4A4 or even W4A8 baselines. "E2E" means the end-to-end latency including the text encoder and VAE decoder.
Method
Quantization Method -- SVDQuant
Overview of SVDQuant. Stage1: Originally, both the activation X and weights W contain outliers, making 4-bit quantization challenging. Stage 2: We migrate the outliers from activations to weights, resulting in the updated activation and weight. While the activation becomes easier to quantize, the weight now becomes more difficult. Stage 3: SVDQuant further decomposes the weight into a low-rank component and a residual with SVD. Thus, the quantization difficulty is alleviated by the low-rank branch, which runs at 16-bit precision.
Nunchaku Engine Design
(a) Naïvely running low-rank branch with rank 32 will introduce 57% latency overhead due to extra read of 16-bit inputs in Down Projection and extra write of 16-bit outputs in Up Projection. Nunchaku optimizes this overhead with kernel fusion. (b) Down Projection and Quantize kernels use the same input, while Up Projection and 4-Bit Compute kernels share the same output. To reduce data movement overhead, we fuse the first two and the latter two kernels together.
Model Description
- Developed by: MIT, NVIDIA, CMU, Princeton, UC Berkeley, SJTU and Pika Labs
- Model type: INT W4A4 model
- Model size: 6.64GB
- Model resolution: The number of pixels need to be a multiple of 65,536.
- License: Apache-2.0
Usage
Diffusers
Please follow the instructions in mit-han-lab/nunchaku to set up the environment. Then you can run the model with
import torch
from nunchaku.pipelines import flux as nunchaku_flux
pipeline = nunchaku_flux.from_pretrained(
"black-forest-labs/FLUX.1-dev",
torch_dtype=torch.bfloat16,
qmodel_path="mit-han-lab/svdq-int4-flux.1-dev", # download from Huggingface
).to("cuda")
image = pipeline("A cat holding a sign that says hello world", num_inference_steps=50, guidance_scale=3.5).images[0]
image.save("example.png")
Comfy UI
Work in progress.
Limitations
- The model is only runnable on NVIDIA GPUs with architectures sm_86 (Ampere: RTX 3090, A6000), sm_89 (Ada: RTX 4090), and sm_80 (A100). See this issue for more details.
- You may observe some slight differences from the BF16 models in details.
Citation
If you find this model useful or relevant to your research, please cite
@article{
li2024svdquant,
title={SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models},
author={Li*, Muyang and Lin*, Yujun and Zhang*, Zhekai and Cai, Tianle and Li, Xiuyu and Guo, Junxian and Xie, Enze and Meng, Chenlin and Zhu, Jun-Yan and Han, Song},
journal={arXiv preprint arXiv:2411.05007},
year={2024}
}