Model · Alibaba · Image-Gen
Qwen-Image-Edit-2511
Alibaba's open photo-editing model: describe the change in plain words and it edits the image, including combining several photos into one. The newest Apache 2.0 Qwen editing model — the later Qwen-Image-2.1 is research-only.
- Modality
- Image-Gen
- License
- Apache 2.0 (Open)
- Parameter size
- 20B (Hugging Face reports 20.4B)
- Released
- December 23, 2025
- Last verified
- October 28, 2026
- Runs locally
- Yes
What you need to run it
- Mac
- Yes. Any Apple Silicon Mac (M1 or newer) with at least 48 GB (64 GB recommended) of memory. Newer chips are faster, but memory is what decides whether it runs.
- Windows / Linux PC
- NVIDIA works best. A graphics card with at least 24 GB (48 GB recommended) of video memory.
- No graphics card
- Not practical. Too slow without a graphics card or Apple Silicon.
Runs on Apple Silicon with the community MLX 8-bit build (about 37 GB of files), but it is large, so plan on a 48 GB Mac or more.
Numbers are for: 20B model: 8-bit Mac build for the minimum; full 16-bit on a PC for recommended. Our estimate from the model’s size — the maker publishes no figure.
Strengths
- Apache 2.0 — free for commercial use with no revenue cap
- Edits from a plain-language instruction, with better character consistency than the 2509 version
- Takes several input images, e.g. merging two separate portraits into one group photo
- Popular community LoRAs are built into the base model, so common effects need no add-on
Weaknesses
- Large at 20B parameters — over three times the size of 6B image models, so plan on a large-memory GPU or a quantised community build; the card states no minimum
- Newer Qwen-Image-2.1 is under the Qwen Research License (non-commercial), so this older model is the one a business can ship
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Apache 2.0 |
| ModelScope | weights | Mirror of the weights |
| Qwen Chat | product | Image Editing feature; free account |
| Hugging Face Spaces | hosted | Free demo |
Official sources
- Model card model
- Announcement announcement
- GitHub github
- Technical report paper
Change log
- — Added hardware requirements (Mac support, memory, NVIDIA). Source: an estimate from the 20B size and the community mlx-community 8-bit build; the model card states no minimum.
- — Initial entry. Released 2025-12-23 per the Qwen-Image GitHub news, under Apache 2.0. Added 2026-10-28 from the popularity sweep: 200k Hugging Face downloads in the last month and 1.5k likes. Qwen-Image-2.1 is newer but under the non-commercial Qwen Research License; Qwen-Image-2512 (2025-12-31, Apache 2.0) is the text-to-image sibling, not an editor.
Esc