Skip to content

[Workers AI] Fix gpt-image-2 input field: image -> images #30526

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
superhighfives merged 1 commit into from
May 4, 2026
+49 −39
Merged

[Workers AI] Fix gpt-image-2 input field: image -> images #30526

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 49 additions & 39 deletions src/content/catalog-models/openai-gpt-image-2.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,7 @@
"name": "OpenAI GPT Image 2",
"description": "OpenAI's next-generation image model that creates and edits images from text prompts, with support for multiple quality levels, sizes, and output formats. Note: transparent backgrounds are not supported \u2014 use openai/gpt-image-1.5 for transparent PNGs.",
"task": "Text-to-Image",
"tags": [
"Image Generation",
"Image Editing",
"Multimodal"
],
"tags": ["Image Generation", "Image Editing", "Multimodal"],
"context_length": null,
"max_output_tokens": null,
"schema_version": "1.0.0",
Expand Down Expand Up @@ -123,10 +119,12 @@
},
{
"name": "Image Edit",
"description": "Edit an existing image by providing it as base64 (a raw string or a data:image/{png|jpeg|webp};base64,... URI). This routes the call to OpenAI's /v1/images/edits endpoint. The example uses a tiny 32x32 smiley-face PNG - real inputs are the full base64 encoding of your source image.",
"description": "Edit an existing image by providing it in the images array as base64 (a raw string or a data:image/{png|jpeg|webp};base64,... URI). This routes the call to OpenAI's /v1/images/edits endpoint. The example uses a tiny 32x32 smiley-face PNG - real inputs are the full base64 encoding of your source image.",
"input": {
"prompt": "Transform this cartoon smiley into a photorealistic 3D clay sculpture sitting on a marble pedestal, studio lighting",
"image": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII="
"images": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII="
]
},
"output": {
"image": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__gpt-image-2/image-edit.png"
Expand All @@ -144,7 +142,37 @@
{
"label": "typescript",
"language": "typescript",
"code": "const response = await env.AI.run(\n 'openai/gpt-image-2',\n {\n prompt:\n 'Transform this cartoon smiley into a photorealistic 3D clay sculpture sitting on a marble pedestal, studio lighting',\n image:\n 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=',\n },\n {\n gateway: { id: 'default' },\n }\n)\nconsole.log(response)"
"code": "const response = await env.AI.run(\n 'openai/gpt-image-2',\n {\n prompt:\n 'Transform this cartoon smiley into a photorealistic 3D clay sculpture sitting on a marble pedestal, studio lighting',\n images: [\n 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=',\n ],\n },\n {\n gateway: { id: 'default' },\n }\n)\nconsole.log(response)"
}
]
},
{
"name": "Multi-Image Edit",
"description": "Compose multiple input images by passing up to 16 base64 strings in the images array. The model blends the references; useful for combining subjects, styles, or reference shots. The example pairs a smiley-face PNG with a red ball PNG.",
"input": {
"prompt": "Combine these into a single photorealistic scene: a ceramic smiley-face mug next to a red rubber ball on a sunlit wooden table",
"images": [
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=",
"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAhklEQVR42u2XsRHAMAgDNY73nye7OG2KgGUnGCWH76j/oTACPfnhcwIA3AoTGIFXRTADPlqjakYEDJwFWyJLAk/hrAQi4YwEouEjiVuBt+FXCVcgqntvCtjVvTUF7OremkIJlEAJ6Aikf0QSX3H6MpJYx+mBRCKSSYRSiVgucZjInGa/vY5PvB72/7IdMuAAAAAASUVORK5CYII="
]
},
"output": {
"image": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__gpt-image-2/multi-image-edit.png"
},
"raw_response": {
"state": "Completed",
"result": {
"image": "https://pub-04a6d208d361438ea01b797e6973bd19.r2.dev/catalog/openai__gpt-image-2/multi-image-edit.png"
},
"gatewayMetadata": {
"keySource": "Unified"
}
},
"code_snippets": [
{
"label": "typescript",
"language": "typescript",
"code": "const response = await env.AI.run(\n 'openai/gpt-image-2',\n {\n prompt:\n 'Combine these into a single photorealistic scene: a ceramic smiley-face mug next to a red rubber ball on a sunlit wooden table',\n images: [\n 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAnklEQVR42u2XQRLAIAgD8/839i/26qFCACm0ozPe1KwcQsAoXvgcAABxpwFowl4QWITHxW0LCBhxVngF4gKIirMQyBRnIJAtrkE8AuwWnyFEgKzfS1UA+3sWTju3BGAu7gKYIfBW+Q/AAQgBeMCkt1wVsLZjcwUYG2Z9wGLHZitWk1DEisubUYt2XB5IWkSyFqG0RSxvMZi0Gc1+Ox3fm00ZJ5mGVtkAAAAASUVORK5CYII=',\n 'data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACAAAAAgCAYAAABzenr0AAAAhklEQVR42u2XsRHAMAgDNY73nye7OG2KgGUnGCWH76j/oTACPfnhcwIA3AoTGIFXRTADPlqjakYEDJwFWyJLAk/hrAQi4YwEouEjiVuBt+FXCVcgqntvCtjVvTUF7OremkIJlEAJ6Aikf0QSX3H6MpJYx+mBRCKSSYRSiVgucZjInGa/vY5PvB72/7IdMuAAAAAASUVORK5CYII=',\n ],\n },\n {\n gateway: { id: 'default' },\n }\n)\nconsole.log(response)"
}
]
}
Expand Down Expand Up @@ -173,52 +201,36 @@
"description": "Text prompt describing the image to generate or edit",
"type": "string"
},
"image": {
"description": "Base64-encoded input image for image editing",
"type": "string"
"images": {
"description": "Input images for image editing, 1-16 entries. Each entry is base64-encoded (raw string or data:image/{png|jpeg|webp};base64,... URI).",
"maxItems": 16,
"type": "array",
"items": {
"type": "string"
}
Comment thread
superhighfives marked this conversation as resolved.
},
"quality": {
"description": "Quality of the generated image",
"type": "string",
"enum": [
"low",
"medium",
"high",
"auto"
]
"enum": ["low", "medium", "high", "auto"]
},
"size": {
"description": "Size of the generated image",
"type": "string",
"enum": [
"1024x1024",
"1024x1536",
"1536x1024",
"auto"
]
"enum": ["1024x1024", "1024x1536", "1536x1024", "auto"]
},
"background": {
"description": "Background transparency setting. Use transparent for images with no background, opaque for a solid background, or auto to let the model decide.",
"type": "string",
"enum": [
"transparent",
"opaque",
"auto"
]
"enum": ["transparent", "opaque", "auto"]
Comment thread
superhighfives marked this conversation as resolved.
},
"output_format": {
"description": "Output format for the generated image",
"type": "string",
"enum": [
"png",
"webp",
"jpeg"
]
"enum": ["png", "webp", "jpeg"]
}
},
"required": [
"prompt"
],
"required": ["prompt"],
"additionalProperties": false
},
"output": {
Expand All @@ -231,9 +243,7 @@
"format": "uri"
}
},
"required": [
"image"
],
"required": ["image"],
"additionalProperties": false
}
}
Expand Down
Loading