Downloads · 30 days
15
20% of all-time downloads
Qwen_Image_Layered_sdnq_dynamic_4bit
OzzyGT/Qwen_Image_Layered_sdnq_dynamic_4bit
Qwen_Image_Layered_sdnq_dynamic_4bit is a text-to-image model from OzzyGT. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
This is an int4 quantized version of Qwen/Qwen-Image-Layered using SDNQ (SD.Next Quantization) with the dynamic option and Hadamard Rotation.
All-time downloads
75
Public
Parameters
10.9B
18.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors18.1 GB · 100%
Parameter types
How the weights are stored.
U810.2B · 93%
Base models
Model card
From the Hugging Face model README
Qwen Image Layered SDNQ Dynamic INT4
This is an int4 quantized version of Qwen/Qwen-Image-Layered using SDNQ (SD.Next Quantization) with the dynamic option and Hadamard Rotation.
Note: You need SDNQ v0.2.0 or superior
Usage
You can find ready-to-use scripts in the diffusers-recipes repository.
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Languages
- en, zh
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026