Instructions to use nunchaku-ai/nunchaku-flux.1-canny-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nunchaku-ai/nunchaku-flux.1-canny-dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nunchaku-ai/nunchaku-flux.1-canny-dev", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Upload ./README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -48,13 +48,12 @@ This repository contains Nunchaku-quantized versions of [FLUX.1-Canny-dev](https
|
|
| 48 |
- [`svdq-int4_r32-flux.1-canny-dev.safetensors`](./svdq-int4_r32-flux.1-canny-dev.safetensors): SVDQuant quantized INT4 FLUX.1-Canny-dev model. For users with non-Blackwell GPUs (pre-50-series).
|
| 49 |
- [`svdq-fp4_r32-flux.1-canny-dev.safetensors`](./svdq-fp4_r32-flux.1-canny-dev.safetensors): SVDQuant quantized NVFP4 FLUX.1-Canny-dev model. For users with Blackwell GPUs (50-series).
|
| 50 |
|
| 51 |
-
|
| 52 |
### Model Sources
|
| 53 |
|
| 54 |
- **Inference Engine:** [nunchaku](https://github.com/nunchaku-tech/nunchaku)
|
| 55 |
- **Quantization Library:** [deepcompressor](https://github.com/nunchaku-tech/deepcompressor)
|
| 56 |
- **Paper:** [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](http://arxiv.org/abs/2411.05007)
|
| 57 |
-
- **Demo:** [
|
| 58 |
|
| 59 |
## Usage
|
| 60 |
|
|
|
|
| 48 |
- [`svdq-int4_r32-flux.1-canny-dev.safetensors`](./svdq-int4_r32-flux.1-canny-dev.safetensors): SVDQuant quantized INT4 FLUX.1-Canny-dev model. For users with non-Blackwell GPUs (pre-50-series).
|
| 49 |
- [`svdq-fp4_r32-flux.1-canny-dev.safetensors`](./svdq-fp4_r32-flux.1-canny-dev.safetensors): SVDQuant quantized NVFP4 FLUX.1-Canny-dev model. For users with Blackwell GPUs (50-series).
|
| 50 |
|
|
|
|
| 51 |
### Model Sources
|
| 52 |
|
| 53 |
- **Inference Engine:** [nunchaku](https://github.com/nunchaku-tech/nunchaku)
|
| 54 |
- **Quantization Library:** [deepcompressor](https://github.com/nunchaku-tech/deepcompressor)
|
| 55 |
- **Paper:** [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](http://arxiv.org/abs/2411.05007)
|
| 56 |
+
- **Demo:** [demo.nunchaku.tech](https://demo.nunchaku.tech)
|
| 57 |
|
| 58 |
## Usage
|
| 59 |
|