GPT Image 2
OpenAI GPT Image 2 — extreme prompt adherence and text rendering. Auto-switches between generate and edit based on inputs. For MAX resolution, set image_size to a custom {width,height} (e.g. {"width":1024,"height":1536}) — the named presets (portrait_16_9 etc.) cap around ~1024px; custom dims go up to 4K (multiples of 16, aspect ≤ 3:1).
GPT Image 2
Badge: New
Node type: generate:openai_gpt_image_2
Category: generate
Description
OpenAI GPT Image 2 — extreme prompt adherence and text rendering. Auto-switches between generate and edit based on inputs. For MAX resolution, set image_size to a custom {width,height} (e.g. {"width":1024,"height":1536}) — the named presets (portrait_16_9 etc.) cap around ~1024px; custom dims go up to 4K (multiples of 16, aspect ≤ 3:1).
Pricing
- Cost: ~44 credits per images
- Notes: Token-metered. Pre-charge by quality+image_size; default high. FAL pricing API returns opaque "$1/units" so we hardcode from docs.
Variant family
- Family:
gpt-image-2 - Is primary: yes
- All variants:
generate:openai_gpt_image_2,edit:openai_gpt_image_2_edit
Canvas ports
These appear as port handles on the left side of the node.
| ID | Label | Details |
|---|---|---|
prompt |
Prompt | TEXT (required) · multiline |
image1 |
Image 1 | IMAGE |
Sidebar config
These render as form fields in the right-side config panel when the node is selected.
| ID | Label | Details |
|---|---|---|
quality |
Quality | TEXT · options: low, medium, high, auto |
image_size |
Image Size | IMAGE_SIZE · options: custom, square_hd, square, portrait_4_3, portrait_16_9, +3 |
num_images |
Number of Images | NUMBER · 1…4 |
output_format |
Output Format | TEXT · options: jpeg, png, webp |
sync_mode |
Sync Mode | BOOLEAN |
Outputs
| ID | Label | Type |
|---|---|---|
images |
Generated Images | IMAGE |
Auto-generated from the Wireflow node registry.