opensource/sim
3
0
Fork 0
mirror of https://github.com/simstudioai/sim.git synced 2026-09-24 15:45:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(image-generator): add gpt-image-2 model support (#4437)

Browse Source 
* feat(image-generator): add gpt-image-2 model support

* docs
This commit is contained in:
Waleed
2026-05-04 15:26:47 -07:00
committed by GitHub
parent ae20d1ce90
commit 6d044a924c
8 changed files with 197 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/docs/content/docs/en/tools/image_generator.mdx
+8 -6
View File
@@ -29,7 +29,7 @@ In Sim, the DALL-E integration enables your agents to generate images programmat
## Usage Instructions
Integrate Image Generator into the workflow. Can generate images using DALL-E 3 or GPT Image.
Integrate Image Generator into the workflow. Can generate images using DALL-E 3, GPT Image 1, or GPT Image 2.
@@ -43,12 +43,14 @@ Generate images using OpenAI
| Parameter | Type | Required | Description |
| --------- | ---- | -------- | ----------- |
| `model` | string | Yes | The model to use \(gpt-image-1 or dall-e-3\) |
| `model` | string | Yes | The model to use \(dall-e-3, gpt-image-1, or gpt-image-2\) |
| `prompt` | string | Yes | A text description of the desired image |
| `size` | string | Yes | The size of the generated images \(1024x1024, 1024x1792, or 1792x1024\) |
| `quality` | string | No | The quality of the image \(standard or hd\) |
| `style` | string | No | The style of the image \(vivid or natural\) |
| `background` | string | No | The background color, only for gpt-image-1 |
| `size` | string | Yes | Image size. dall-e-3: 1024x1024, 1024x1792, or 1792x1024. gpt-image-1: auto, 1024x1024, 1536x1024, or 1024x1536. gpt-image-2: auto or any size with edges ≤3840px and multiples of 16 \(e.g. 1024x1024, 1536x1024, 1024x1536, 2560x1440, 3840x2160\). |
| `quality` | string | No | Quality. dall-e-3: standard\|hd. gpt-image-1/gpt-image-2: auto\|low\|medium\|high |
| `style` | string | No | The style of the image \(vivid or natural\), only for dall-e-3 |
| `background` | string | No | Background. gpt-image-1: auto\|transparent\|opaque. gpt-image-2: auto\|opaque \(transparent not supported\) |
| `outputFormat` | string | No | Output image format \(png, jpeg, webp\), only for gpt-image-1 and gpt-image-2 |
| `moderation` | string | No | Moderation level \(auto or low\), only for gpt-image-1 and gpt-image-2 |
| `n` | number | No | The number of images to generate \(1-10\) |
| `apiKey` | string | Yes | Your OpenAI API key |
apps/docs/content/docs/en/tools/knowledge.mdx
+2
View File
@@ -49,6 +49,8 @@ Search for similar content in a knowledge base using vector similarity
| `tagValue` | string | No | No description |
| `rerankerEnabled` | boolean | No | Whether to apply Cohere reranking to vector search results |
| `rerankerModel` | string | No | Cohere rerank model to use \(one of: rerank-v4.0-pro, rerank-v4.0-fast, rerank-v3.5\) |
| `rerankerInputCount` | number | No | Number of vector results sent to the Cohere reranker \(1–100\). Defaults to topK × 4 capped at 100. |
| `apiKey` | string | No | Cohere API key for reranker \(self-hosted deployments only\) |
| `tagFilters` | string | No | No description |
#### Output
apps/docs/content/docs/en/tools/mem0.mdx
+7 -10
View File
@@ -50,12 +50,9 @@ Add memories to Mem0 for persistent storage and retrieval
| Parameter | Type | Description |
| --------- | ---- | ----------- |
| `ids` | array | Array of memory IDs that were created |
| `memories` | array | Array of memory objects that were created |
| ↳ `id` | string | Unique identifier for the memory |
| ↳ `memory` | string | The content of the memory |
| ↳ `event` | string | Event type indicating operation performed \(ADD, UPDATE, DELETE, NOOP\) |
| ↳ `metadata` | json | Custom metadata associated with the memory |
| `message` | string | Status message for the queued memory processing job |
| `status` | string | Processing status returned by Mem0 |
| `event_id` | string | Event ID for polling memory processing status |
### `mem0_search_memories`
@@ -102,6 +99,7 @@ Retrieve memories from Mem0 by ID or filter criteria
| `startDate` | string | No | Start date for filtering by created_at \(e.g., "2024-01-15"\) |
| `endDate` | string | No | End date for filtering by created_at \(e.g., "2024-12-31"\) |
| `limit` | number | No | Maximum number of results to return \(e.g., 10, 50, 100\) |
| `page` | number | No | Page number to retrieve for paginated list results |
| `apiKey` | string | Yes | Your Mem0 API key |
#### Output
@@ -120,10 +118,9 @@ Retrieve memories from Mem0 by ID or filter criteria
| ↳ `categories` | json | Auto-assigned categories for the memory |
| ↳ `created_at` | string | ISO 8601 timestamp when the memory was created |
| ↳ `updated_at` | string | ISO 8601 timestamp when the memory was last updated |
| ↳ `owner` | string | Owner of the memory |
| ↳ `organization` | string | Organization associated with the memory |
| ↳ `immutable` | boolean | Whether the memory can be modified |
| ↳ `expiration_date` | string | Expiration date after which memory is not retrieved |
| `ids` | array | Array of memory IDs that were retrieved |
| `count` | number | Total number of memories matching the filters |
| `next` | string | URL for the next page of results |
| `previous` | string | URL for the previous page of results |
apps/docs/content/docs/en/triggers/meta.json
+1
View File
@@ -39,6 +39,7 @@
"servicenow",
"slack",
"stripe",
"table",
"telegram",
"twilio_voice",
"typeform",
apps/docs/content/docs/en/triggers/table.mdx
+45
View File
@@ -0,0 +1,45 @@
---
title: Table
description: Available Table triggers for automating workflows
---
import { BlockInfoCard } from "@/components/ui/block-info-card"
<BlockInfoCard
type="table"
color="#10B981"
/>
Table provides 1 trigger for automating workflows based on events.
## Triggers
### Table Trigger
Triggers when rows are inserted or updated in a table
#### Configuration
| Parameter | Type | Required | Description |
| --------- | ---- | -------- | ----------- |
| `tableSelector` | table-selector | Yes | The table to monitor. |
| `manualTableId` | string | Yes | The table to monitor. |
| `eventType` | string | Yes | The type of event to trigger on. |
| `watchColumns` | string | No | Only fire when these columns change. Leave empty to fire on any update. |
| `includeHeaders` | boolean | No | When enabled, each row is returned as a key-value object mapped to column names. |
#### Output
| Parameter | Type | Description |
| --------- | ---- | ----------- |
| `row` | json | Row data mapped to column names \(when header mapping is enabled\) |
| `rawRow` | json | Raw row data object |
| `previousRow` | json | Previous row data before the update \(null for inserts\) |
| `changedColumns` | json | List of column names that changed \(empty for inserts\) |
| `rowId` | string | The unique row ID |
| `headers` | json | Column names from the table schema |
| `rowNumber` | number | The position of the row in the table |
| `tableId` | string | The table ID |
| `tableName` | string | The table name |
| `timestamp` | string | Event timestamp in ISO format |
apps/sim/app/(landing)/integrations/data/integrations.json
+2 -2
View File
@@ -6496,7 +6496,7 @@
"slug": "image-generator",
"name": "Image Generator",
"description": "Generate images",
"longDescription": "Integrate Image Generator into the workflow. Can generate images using DALL-E 3 or GPT Image.",
"longDescription": "Integrate Image Generator into the workflow. Can generate images using DALL-E 3, GPT Image 1, or GPT Image 2.",
"bgColor": "#4D5FFF",
"iconName": "ImageIcon",
"docsUrl": "https://docs.sim.ai/tools/image_generator",
@@ -7540,7 +7540,7 @@
"operationCount": 14,
"triggers": [],
"triggerCount": 0,
"authType": "none",
"authType": "api-key",
"category": "blocks"
},
{
apps/sim/blocks/blocks/image_generator.ts
+107 -10
View File
@@ -8,7 +8,7 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
description: 'Generate images',
authMode: AuthMode.ApiKey,
longDescription:
'Integrate Image Generator into the workflow. Can generate images using DALL-E 3 or GPT Image.',
'Integrate Image Generator into the workflow. Can generate images using DALL-E 3, GPT Image 1, or GPT Image 2.',
docsLink: 'https://docs.sim.ai/tools/image_generator',
category: 'tools',
integrationType: IntegrationType.AI,
@@ -22,7 +22,8 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
type: 'dropdown',
options: [
{ label: 'DALL-E 3', id: 'dall-e-3' },
{ label: 'GPT Image', id: 'gpt-image-1' },
{ label: 'GPT Image 1', id: 'gpt-image-1' },
{ label: 'GPT Image 2', id: 'gpt-image-2' },
],
value: () => 'dall-e-3',
},
@@ -60,6 +61,22 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
condition: { field: 'model', value: 'gpt-image-1' },
dependsOn: ['model'],
},
{
id: 'size',
title: 'Size',
type: 'dropdown',
options: [
{ label: 'Auto', id: 'auto' },
{ label: 'Square (1024x1024)', id: '1024x1024' },
{ label: 'Portrait (1024x1536)', id: '1024x1536' },
{ label: 'Landscape (1536x1024)', id: '1536x1024' },
{ label: '2K (2560x1440)', id: '2560x1440' },
{ label: '4K (3840x2160)', id: '3840x2160' },
],
value: () => 'auto',
condition: { field: 'model', value: 'gpt-image-2' },
dependsOn: ['model'],
},
{
id: 'quality',
title: 'Quality',
@@ -72,6 +89,20 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
condition: { field: 'model', value: 'dall-e-3' },
dependsOn: ['model'],
},
{
id: 'quality',
title: 'Quality',
type: 'dropdown',
options: [
{ label: 'Auto', id: 'auto' },
{ label: 'Low', id: 'low' },
{ label: 'Medium', id: 'medium' },
{ label: 'High', id: 'high' },
],
value: () => 'auto',
condition: { field: 'model', value: ['gpt-image-1', 'gpt-image-2'] },
dependsOn: ['model'],
},
{
id: 'style',
title: 'Style',
@@ -97,6 +128,43 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
condition: { field: 'model', value: 'gpt-image-1' },
dependsOn: ['model'],
},
{
id: 'background',
title: 'Background',
type: 'dropdown',
options: [
{ label: 'Auto', id: 'auto' },
{ label: 'Opaque', id: 'opaque' },
],
value: () => 'auto',
condition: { field: 'model', value: 'gpt-image-2' },
dependsOn: ['model'],
},
{
id: 'outputFormat',
title: 'Output Format',
type: 'dropdown',
options: [
{ label: 'PNG', id: 'png' },
{ label: 'JPEG', id: 'jpeg' },
{ label: 'WebP', id: 'webp' },
],
value: () => 'png',
condition: { field: 'model', value: ['gpt-image-1', 'gpt-image-2'] },
dependsOn: ['model'],
},
{
id: 'moderation',
title: 'Moderation',
type: 'dropdown',
options: [
{ label: 'Auto', id: 'auto' },
{ label: 'Low', id: 'low' },
],
value: () => 'auto',
condition: { field: 'model', value: ['gpt-image-1', 'gpt-image-2'] },
dependsOn: ['model'],
},
{
id: 'apiKey',
title: 'API Key',
@@ -120,7 +188,25 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
}
const model = params.model || 'dall-e-3'
const size = params.size || (model === 'gpt-image-1' ? 'auto' : '1024x1024')
const ALLOWED_SIZES: Record<string, string[]> = {
'dall-e-3': ['1024x1024', '1024x1792', '1792x1024'],
'gpt-image-1': ['auto', '1024x1024', '1536x1024', '1024x1536'],
'gpt-image-2': ['auto', '1024x1024', '1536x1024', '1024x1536', '2560x1440', '3840x2160'],
}
const ALLOWED_QUALITIES: Record<string, string[]> = {
'dall-e-3': ['standard', 'hd'],
'gpt-image-1': ['auto', 'low', 'medium', 'high'],
'gpt-image-2': ['auto', 'low', 'medium', 'high'],
}
const ALLOWED_BACKGROUNDS: Record<string, string[]> = {
'gpt-image-1': ['auto', 'transparent', 'opaque'],
'gpt-image-2': ['auto', 'opaque'],
}
const defaultSize = model === 'dall-e-3' ? '1024x1024' : 'auto'
const size = ALLOWED_SIZES[model]?.includes(params.size) ? params.size : defaultSize
const baseParams = {
prompt: params.prompt,
model,
@@ -129,16 +215,25 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
}
if (model === 'dall-e-3') {
return {
...baseParams,
quality: params.quality || 'standard',
style: params.style || 'vivid',
}
const quality = ALLOWED_QUALITIES['dall-e-3'].includes(params.quality)
? params.quality
: 'standard'
const style = ['vivid', 'natural'].includes(params.style) ? params.style : 'vivid'
return { ...baseParams, quality, style }
}
if (model === 'gpt-image-1') {
if (model === 'gpt-image-1' || model === 'gpt-image-2') {
const quality = ALLOWED_QUALITIES[model].includes(params.quality)
? params.quality
: undefined
const background = ALLOWED_BACKGROUNDS[model].includes(params.background)
? params.background
: undefined
return {
...baseParams,
...(params.background && { background: params.background }),
...(quality && { quality }),
...(background && { background }),
...(params.outputFormat && { outputFormat: params.outputFormat }),
...(params.moderation && { moderation: params.moderation }),
}
}
@@ -153,6 +248,8 @@ export const ImageGeneratorBlock: BlockConfig<DalleResponse> = {
quality: { type: 'string', description: 'Image quality level' },
style: { type: 'string', description: 'Image style' },
background: { type: 'string', description: 'Background type' },
outputFormat: { type: 'string', description: 'Output image format (png, jpeg, webp)' },
moderation: { type: 'string', description: 'Moderation level (auto or low)' },
apiKey: { type: 'string', description: 'OpenAI API key' },
},
outputs: {
apps/sim/tools/openai/image.ts
+25 -8
View File
@@ -16,7 +16,7 @@ export const imageTool: ToolConfig = {
type: 'string',
required: true,
visibility: 'user-only',
description: 'The model to use (gpt-image-1 or dall-e-3)',
description: 'The model to use (dall-e-3, gpt-image-1, or gpt-image-2)',
},
prompt: {
type: 'string',
@@ -28,25 +28,39 @@ export const imageTool: ToolConfig = {
type: 'string',
required: true,
visibility: 'user-or-llm',
description: 'The size of the generated images (1024x1024, 1024x1792, or 1792x1024)',
description:
'Image size. dall-e-3: 1024x1024, 1024x1792, or 1792x1024. gpt-image-1: auto, 1024x1024, 1536x1024, or 1024x1536. gpt-image-2: auto or any size with edges ≤3840px and multiples of 16 (e.g. 1024x1024, 1536x1024, 1024x1536, 2560x1440, 3840x2160).',
},
quality: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'The quality of the image (standard or hd)',
description: 'Quality. dall-e-3: standard|hd. gpt-image-1/gpt-image-2: auto|low|medium|high',
},
style: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'The style of the image (vivid or natural)',
description: 'The style of the image (vivid or natural), only for dall-e-3',
},
background: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'The background color, only for gpt-image-1',
description:
'Background. gpt-image-1: auto|transparent|opaque. gpt-image-2: auto|opaque (transparent not supported)',
},
outputFormat: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Output image format (png, jpeg, webp), only for gpt-image-1 and gpt-image-2',
},
moderation: {
type: 'string',
required: false,
visibility: 'user-or-llm',
description: 'Moderation level (auto or low), only for gpt-image-1 and gpt-image-2',
},
n: {
type: 'number',
@@ -73,15 +87,18 @@ export const imageTool: ToolConfig = {
const body: BaseImageRequestBody = {
model: params.model,
prompt: params.prompt,
size: params.size || '1024x1024',
size: params.size || (params.model === 'dall-e-3' ? '1024x1024' : 'auto'),
n: params.n ? Number(params.n) : 1,
}
if (params.model === 'dall-e-3') {
if (params.quality) body.quality = params.quality
if (params.style) body.style = params.style
} else if (params.model === 'gpt-image-1') {
} else if (params.model === 'gpt-image-1' || params.model === 'gpt-image-2') {
if (params.quality) body.quality = params.quality
if (params.background) body.background = params.background
if (params.outputFormat) body.output_format = params.outputFormat
if (params.moderation) body.moderation = params.moderation
}
return body
@@ -111,7 +128,7 @@ export const imageTool: ToolConfig = {
} else if (data.data?.[0]?.b64_json) {
base64Image = data.data[0].b64_json
logger.info(
'Found base64 encoded image in response for GPT-Image-1',
`Found base64 encoded image in response for ${modelName}`,
`length: ${base64Image.length}`
)
} else {