Qwen Image Edit
AI generationAlibabaEdit images with text instructions. No mask needed - just describe the change.
- Runs
- On our servers
- Typical time
- 5-20s
- Inputs
- 2
- Outputs
- 1
Inputs
| Port | Type | ID |
|---|---|---|
| Prompt | text | prompt-in |
| Reference | image | image-in |
Outputs
| Port | Type | ID |
|---|---|---|
| Image | image | image-out |
Settings
| Setting | Type | Default | Options |
|---|---|---|---|
| Aspect RatioOutput dimensions | select | landscape_16_9 | 16:9 Landscape, 9:16 Portrait, 1:1 Square, 1:1 Square HD |
| StepsMore steps = finer detail, slower render | slider | 15 | 10 to 50 |
| Guidance ScaleHow closely the result follows your prompt | slider | 4 | 1 to 10 |
| SeedFixed number for reproducible results, 0 = random | number | 0 | 0 to 2147483647 |
Prompting
Describe the edit (e.g., "change the sky to sunset", "remove the person")...
Maximum prompt length: 2000 characters.
What this connects into (24)
Computed from the port compatibility rules, so it stays correct as nodes change.
- Flux LoRA
- Nano Banana 2
- Nano Banana Pro
- GPT Image 2
- Gemini Omni
- Seedance 2.0
- Grok Imagine 1.5 I2V
- Kling 3.0 I2V
- Kling 3.0 Pro I2V
- Kling O3 I2V
- Kling O1 FLF2V
- WAN 2.7 I2V
- HappyHorse 1.0 I2V
- WAN Pro I2V
- WAN Effects
- Seedance 2.0 I2V
- Vidu Q1 FLF2V
- Kling O3 Reference
- Kling O1 Reference
- Seedance 2.0 Reference
- Hyper3D Rodin
- Hunyuan3D v3
- Trellis
- SHARP Gaussian
Node ID qwen-image-edit. Open it in Studio with Tab, then type the name.