Model reference · open weights
Qwen-Image-2512 is an open-weight image model from Qwen, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
💜 <a href="https://chat.qwen.ai/"<bQwen Chat</b</a   |   🤗 <a href="https://huggingface.co/Qwen/Qwen-Image-2512"Hugging Face</a   |   🤖 <a href="https://modelscope.cn/models/Qwen/Qwen-Image-2512"ModelScope</a   |    📑 <a href="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/QwenImage.pdf"Tech Report</a    |    📑 <a href="https://qwen.ai/blog?id=qwen-image-2512"Blog</a    🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen-Image-2512"Demo</a   |   💬 <a href="https://github.com/QwenLM/Qwen-Image/blob/main/assets/wechat.png"WeChat (微信)</a   |   🫨 <a href="https://discord.gg/CV4E9rpNSD"Discord</a  |    <a href="https://github.com/QwenLM/Qwen-Image"Github</a   Introduction We are excited to introduce Qwen-Image-2512, the December update of Qwen-Image’s text-to-image foundational model. You are welcome to try the latest model at Qwen Chat. Compared to the base Qwen-Image model released in August, Qwen-Image-2512 features the following key improvements: Enhanced Huamn Realism Qwen-Image-2512 significantly reduces the “AI-generated” look and substantially enhances overall image realism, especially for human subjects. Finer Natural Detail Qwen-Image-2512 delivers notably more detailed rendering of landscapes, animal fur, and other natural elements. Improved Text Rendering Qwen-Image-2512 improves the accuracy and quality of textual elements, achieving better layout and more faithful multimodal (text + image) composition. Model Performance We conducted over 10,000 rounds of blind model evaluations on AI Arena, and the results show that Qwen-Image-2512 is currently the strongest open-source model—while remaining highly competitive even among closed-source models. Quick Start Install the latest version of diffusers The following contains a code snippet illustrating how to use Qwen-Image-2512: Showcase Enhanced Huamn Realism In Qwen-Image-2512, human depiction has been substantially refined. Compared to the August release, Qwen-Image-2512 adds significantly richer facial details and better environmental context. For example: A Chinese fem
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Qwen |
|---|---|
| Type | Image models |
| Parameters (lead) | 20.4B |
| Variants | 1 |
| Runs with | diffusers |
| Released | 2025-12-30 |
| Popularity | 85k downloads / month |
| Likes | 930 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Qwen-Image-2512 | 20.4B | BF16 | ~47 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys qwen-image-2512 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qwen-image-2512 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen-image-2512","prompt":"a red bicycle","size":"1024x1024"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗