Downloads · 30 days
0
Qwen-Image-INT8
Winnougan/Qwen-Image-INT8
Qwen-Image-INT8 is a text-to-image model from Winnougan. Use it when you need an image from a text prompt. The card lists the license as apache-2.0.
Access
Public
Updated Jun 30, 2026
Repo size
101 GB
Likes
13
Public
Repo makeup
Click a slice to open those files.
.safetensors50.7 GB · 100%
At a glance
- Task
- Text-to-Image
- License
- apache-2.0
- Access
- Public
- Created
- Jun 28, 2026
- Updated
- Jun 30, 2026
- SHA
- 9916188c
Base models
Model card
From the Hugging Face model README
Qwen Image INT8 ConvRot — ComfyUI Ready
INT8 ConvRot quantized versions of Qwen-Image-2512, Qwen-Image-Edit-2511, and their shared Qwen2.5-VL-7B text encoder for use in ComfyUI. Quantized using silveroxides/convert_to_quant.
Roughly half the VRAM of the BF16 originals with no meaningful quality loss.
What's Included
| File | Description | Folder |
|---|---|---|
qwen_image_2512_int8_convrot.safetensors | Qwen-Image-2512 diffusion model | diffusion_models/ |
qwen_image_edit_2511_int8_convrot.safetensors | Qwen-Image-Edit-2511 diffusion model | diffusion_models/ |
qwen_2.5_vl_7b_int8_convrot.safetensors | Qwen2.5-VL-7B text encoder | text_encoders/ |
- Task
- Text-to-Image
- License
- apache-2.0
- Languages
- en, zh
- Created
- Jun 28, 2026
- Updated
- Jun 30, 2026