Qwimage
A Q4_K_M GGUF quantization of Qwen/Qwen-Image-2.1, with text encoder and VAE files included in this repository.
Files
| Component | Format | Size |
|---|---|---|
| Image model | GGUF Q4_K_M | 4.6 GB |
| Text encoder | Safetensors BF16 | 17.5 GB |
| VAE | Safetensors BF16 | 676 MB |
Content filtering
This release is described as uncensored. Content filtering, prompt handling, and output behavior depend on the application and execution environment. The GGUF format alone does not establish that all prompts will succeed or that outputs will never be filtered.
Source and build
- Source model: Qwen/Qwen-Image-2.1
- Text encoder and VAE source: Comfy-Org/Qwen-Image-2.1
- Source revision:
b3179ad355be050328e483a9dfdd9e60cd62adfa - Conversion: stable-diffusion.cpp commit
1330cebae8f2ba99249df846cc0c9444fcbd4308 - License: Qwen Research License
The revision and conversion identifiers above are retained from the original release description.
Checksums
A SHA256SUMS manifest is not currently included in this repository.
- Downloads last month
- 10
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for VocaborSilentii/Qwimage
Base model
Qwen/Qwen-Image-2.1