How to run Qwen Image Edit without a GPU
How can I run Qwen Image Edit without a GPU or a local install?
Qwen Image Edit has open weights, so you can run it yourself, but you need the hardware: in ComfyUI's tests the fp8 version used most of a 24GB card. Without a GPU, the simplest route is a hosted version. In OTOY Studio, Qwen Image Edit runs in the browser from 6 credits (€0.06) per run, with nothing to install, on the same canvas as 100+ other image, video and 3D models.
Alibaba's instruction-based image editor. It edits from a text instruction, combines several input images, and keeps a product or character consistent, including from new camera angles.
Running it yourself
| Open weights | Qwen-Image-Edit-2509 and 2511 are on Hugging Face. (Qwen Image 3, the newer text-to-image model, is API-only.) |
| License | Apache 2.0. Commercial use is allowed. |
| Hardware | Qwen does not state a minimum. The official README points to DiffSynth-Studio for layer-by-layer offload that runs within 4GB of VRAM, slowly. In ComfyUI's measurements of the base Qwen-Image model, the fp8 file is 20.4GB and used 86% of a 24GB RTX 4090D. |
| Operating system | NVIDIA GPU recommended. |
| ComfyUI | Yes, natively, including the 2511 release. |
Sources: Qwen-Image on GitHub, Qwen-Image-Edit-2509 on Hugging Face, ComfyUI Qwen Image Edit tutorial. Checked October 16, 2026.
Run it yourself if: You have a 24GB GPU and edit images in volume, or want to stack LoRAs from the community.
Running it without a GPU in OTOY Studio
| Node | Takes | Credits per run |
|---|---|---|
| Qwen Image Edit Plus | Prompt plus image | 11 (from €0.11) |
| Qwen Image Edit Plus: Multiple Angles | Prompt plus image | 6 (from €0.06) |
- Sign up free at https://app.otoy.studio. The free plan includes 100 credits a month, no credit card.
- Add a Qwen Image Edit node to a canvas and connect your inputs.
- Run it. It runs on OTOY Studio's hosted GPUs, so your machine only needs a browser.
- Chain the output into other models in the same workflow, or download it.
1 credit = €0.01. Prices are list prices before plan discounts (paid plans take 10% to 25% off every run). Model page: Qwen Image.
Related
Hardware and license details are from each model's official repository and model card, checked October 16, 2026. Prices are computed from OTOY Studio's billing configuration, exported 2026-10-20.