Downloads · 30 days
242
41% of all-time downloads
Qwen-Image-2.1-SDNQ-4bit-dynamic-hadamard256
SamuelTallet/Qwen-Image-2.1-SDNQ-4bit-dynamic-hadamard256
Qwen-Image-2.1-SDNQ-4bit-dynamic-hadamard256 is a image-to-image model from SamuelTallet. Use it when you need one image transformed into another. It is set up for diffusers. The card lists the license as other.
This is Qwen-Image-2.1 optimized using SDNQ with UINT4 dynamic quantization and Hadamard Rotation (Group size: 256).
All-time downloads
588
Public
Parameters
3.8B
12.2 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors11.5 GB · 100%
Parameter types
How the weights are stored.
U83.5B · 92%
Base models
Model card
From the Hugging Face model README
This is Qwen-Image-2.1 optimized using SDNQ with UINT4 dynamic quantization and Hadamard Rotation (Group size: 256).
Texture fix VAE made by Ollin Boer Bohan is included to avoid the checkerboard artefacts in outputs.
Sample
<img src="sample.png">Prompt:
Close portrait of a guitarist sitting on a bench in a lush green park, softly playing an acoustic guitar. Surrounding him are tall trees, a few fallen leaves, and a peaceful pathway. Golden late-afternoon light, a calm and warm atmosphere, cinematic rendering, realistic details, and natural depth of field.
Seed: 616477
Usage
Install Torch, Diffusers (Git), SDNQ 0.2.0+ and Triton.
40 steps.
- Task
- Image-to-Image
- Library
- diffusers
- License
- other
- Created
- Sep 20, 2026
- Updated
- Sep 30, 2026