GPT Image 2
AI generationOpenAIOpenAI image generation with strong instruction following, text rendering, and up to 16 reference images.
- Runs
- On our servers
- Typical time
- 15-60s
- Inputs
- 8
- Outputs
- 1
Inputs
| Port | Type | ID |
|---|---|---|
| Prompt | text | prompt-in |
| Reference 1optional | image | image-in |
| Reference 2optional | image | image-2 |
| Reference 3optional | image | image-3 |
| Reference 4optional | image | image-4 |
| Reference 5optional | image | image-5 |
| Reference 6optional | image | image-6 |
| Reference 7optional | image | image-7 |
Outputs
| Port | Type | ID |
|---|---|---|
| Image | image | image-out |
Settings
| Setting | Type | Default | Options |
|---|---|---|---|
| Aspect RatioOutput shape | select | 1:1 | 1:1 Square, 16:9 Landscape, 9:16 Portrait, 4:3 Standard, 3:4 Portrait, 3:2 Photo, 2:3 Portrait Photo, 21:9 Ultrawide, Auto (1K only) |
| ResolutionOutput resolution | select | 1K | 1K, 2K, 4K (not for 1:1 or auto) |
Prompting
Describe your image. Excels at precise instruction following and text rendering. Connect up to 16 reference images for consistency.
Maximum prompt length: 20000 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
- 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
- Clarity Upscaler
Node ID gpt-image-2. Open it in Studio with Tab, then type the name.