Image Generation

Base URL: https://app.neuroflash.com/api/ds-prototypes

Pay-As-You-Go

Image generation is not yet available in the Pay-As-You-Go plan. It is currently only accessible through subscription plans that include image generation credits.

Generate Text2Image

POST/

Generate images from text prompts (text-to-image).

This endpoint mimics the fal.ai nano-banana API interface.

Request Body

promptstringYesThe text prompt to generate an image from

num_imagesintegerNoThe number of images to generate

aspect_ratiostringNoAspect ratio options for generated images

output_formatstringNoOutput format options for generated images

modelobjectNoThe model to use for image generation

limit_generationsbooleanNoLimit the number of generations to 1

Response

imagesarray<object>The generated images

urlstringThe URL where the file can be downloaded from

content_typestringThe mime type of the file

file_nameobjectThe name of the file

file_sizeobjectThe size of the file in bytes

widthobjectThe width of the image

heightobjectThe height of the image

image_idobjectThe unique ID of the image in storage

descriptionstringThe description of the generated images

promptstringThe prompt used to generate the images

detailobjectOptional detail message (e.g., quota warnings)

batch_idobjectBatch ID for grouping multiple images from one generation

Example

cURL
Python
Node.js
Go

curl -X POST "https://app.neuroflash.com/api/ds-prototypes/" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{
      "prompt": "string",
      "num_images": 1,
      "aspect_ratio": "string",
      "output_format": "string",
      "model": {},
      "limit_generations": false
  }'

import requests

response = requests.post(
    f"https://app.neuroflash.com/api/ds-prototypes/",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id, "Content-Type": "application/json"},
    json={
        "prompt": "string",
        "num_images": 1,
        "aspect_ratio": "string",
        "output_format": "string",
        "model": {},
        "limit_generations": False
    },
).json()

const response = await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/`,
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${token}`,
      "x-workspace-id": workspaceId,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
          "prompt": "string",
          "num_images": 1,
          "aspect_ratio": "string",
          "output_format": "string",
          "model": {},
          "limit_generations": false
    }),
  }
).then((r) => r.json());

body, _ := json.Marshal(map[string]any{
		"prompt": "string",
		"num_images": 1,
		"aspect_ratio": "string",
		"output_format": "string",
		"model": map[string]any{},
		"limit_generations": false,
	})

req, _ := http.NewRequest("POST", "https://app.neuroflash.com/api/ds-prototypes/", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)
req.Header.Set("Content-Type", "application/json")

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Response:

{
  "images": [
    {
      "url": "string",
      "content_type": "string",
      "file_name": {},
      "file_size": {},
      "width": {},
      "height": {},
      "image_id": {}
    }
  ],
  "description": "string",
  "prompt": "string",
  "detail": {},
  "batch_id": {}
}

Generate Image2Image

POST/edit

Generate images from existing images and prompts (image-to-image).

This endpoint mimics the fal.ai nano-banana edit API interface.

Request Body

promptstringYesThe prompt for image editing

num_imagesintegerNoThe number of images to generate

aspect_ratiostringNoAspect ratio options with auto for image editing

output_formatstringNoOutput format options for generated images

modelobjectNoThe model to use for image generation

image_urlsarray<string>YesRelative paths of source images, taken from the output_image_url field returned by the /history endpoint. Do not pass absolute URLs.

limit_generationsbooleanNoLimit the number of generations to 1

Response

imagesarray<object>The generated images

urlstringThe URL where the file can be downloaded from

content_typestringThe mime type of the file

file_nameobjectThe name of the file

file_sizeobjectThe size of the file in bytes

widthobjectThe width of the image

heightobjectThe height of the image

image_idobjectThe unique ID of the image in storage

descriptionstringThe description of the generated images

promptstringThe prompt used to generate the images

detailobjectOptional detail message (e.g., quota warnings)

batch_idobjectBatch ID for grouping multiple images from one generation

Example

Use relative paths from history, not absolute URLs

The image_urls field expects the relative path returned in output_image_url from the /history endpoint — for example /api/ds-prototypes/image_generation/{image_id}/view. Do not construct absolute URLs (e.g. https://app.neuroflash.com/api/...). The image service resolves these paths internally and will return a 500 error if given an external URL.

Typical workflow:

Generate an image with POST / (text-to-image)
Retrieve its output_image_url from GET /history
Pass that relative path in image_urls to POST /edit

cURL
Python
Node.js
Go

curl -X POST "https://app.neuroflash.com/api/ds-prototypes/edit" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{
      "prompt": "string",
      "num_images": 1,
      "aspect_ratio": "string",
      "output_format": "string",
      "model": {},
      "image_urls": ["/api/ds-prototypes/image_generation/YOUR_IMAGE_ID/view"],
      "limit_generations": false
  }'

import requests

response = requests.post(
    f"https://app.neuroflash.com/api/ds-prototypes/edit",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id, "Content-Type": "application/json"},
    json={
        "prompt": "string",
        "num_images": 1,
        "aspect_ratio": "string",
        "output_format": "string",
        "model": {},
        "image_urls": ["/api/ds-prototypes/image_generation/YOUR_IMAGE_ID/view"],
        "limit_generations": False
    },
).json()

const response = await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/edit`,
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${token}`,
      "x-workspace-id": workspaceId,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
          "prompt": "string",
          "num_images": 1,
          "aspect_ratio": "string",
          "output_format": "string",
          "model": {},
          "image_urls": ["/api/ds-prototypes/image_generation/YOUR_IMAGE_ID/view"],
          "limit_generations": false
    }),
  }
).then((r) => r.json());

body, _ := json.Marshal(map[string]any{
		"prompt": "string",
		"num_images": 1,
		"aspect_ratio": "string",
		"output_format": "string",
		"model": map[string]any{},
		"image_urls": []any{"/api/ds-prototypes/image_generation/YOUR_IMAGE_ID/view"},
		"limit_generations": false,
	})

req, _ := http.NewRequest("POST", "https://app.neuroflash.com/api/ds-prototypes/edit", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)
req.Header.Set("Content-Type", "application/json")

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Response:

{
  "images": [
    {
      "url": "string",
      "content_type": "string",
      "file_name": {},
      "file_size": {},
      "width": {},
      "height": {},
      "image_id": {}
    }
  ],
  "description": "string",
  "prompt": "string",
  "detail": {},
  "batch_id": {}
}

Get Available Models

GET/models

Get list of available image generation models.

Returns static list of configured models with allowed flag based on user permissions.

Example

cURL
Python
Node.js
Go

curl "https://app.neuroflash.com/api/ds-prototypes/models" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID"

import requests

response = requests.get(
    f"https://app.neuroflash.com/api/ds-prototypes/models",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id},
).json()

const response = await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/models`,
  { headers: { Authorization: `Bearer ${token}`, "x-workspace-id": workspaceId } }
).then((r) => r.json());

req, _ := http.NewRequest("GET", "https://app.neuroflash.com/api/ds-prototypes/models", nil)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Response:

[
  {
    "id": "string",
    "name": "string",
    "provider": "string",
    "description": "string",
    "capabilities": [
      "string"
    ],
    "max_images": 0,
    "aspect_ratios": [
      "string"
    ],
    "output_formats": [
      "string"
    ],
    "allowed": false,
    "order": 0
  }
]

Get Generation History

GET/history

Get image generation history for the authenticated user's workspace.

Args: model: Optional filter by model name (e.g., "nano-banana") limit: Maximum number of results (default 100, max 1000) offset: Offset for pagination (default 0)

Returns: List of generation history entries

Query Parameters

Parameter	Type	Default
`model`	string	—
`limit`	integer	`100`
`offset`	integer	`0`

Example

cURL
Python
Node.js
Go

curl "https://app.neuroflash.com/api/ds-prototypes/history" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID"

import requests

response = requests.get(
    f"https://app.neuroflash.com/api/ds-prototypes/history",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id},
).json()

const response = await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/history`,
  { headers: { Authorization: `Bearer ${token}`, "x-workspace-id": workspaceId } }
).then((r) => r.json());

req, _ := http.NewRequest("GET", "https://app.neuroflash.com/api/ds-prototypes/history", nil)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Response:

[
  {
    "output_image_id": "string",
    "batch_id": "string",
    "user_id": 0,
    "workspace_id": "string",
    "prompt": "string",
    "model": "string",
    "parameters": {},
    "input_images": {},
    "output_image_url": "/api/ds-prototypes/image_generation/b64b61f6-a7d2-4fa0-9f88-289dae46c41f/view",
    "output_image_width": {},
    "output_image_height": {},
    "output_image_size": {},
    "created_at": "2024-01-15T10:30:00Z"
  }
]

Get Generation By Id

GET/history/{image_id}

Get a specific generation by its image ID.

Args: image_id: The output image ID (also the generation ID)

Returns: Generation history entry

Path Parameters

Parameter	Type	Required	Description
`image_id`	string	Yes

Response

output_image_idstring

batch_idstring

user_idinteger

workspace_idstring

promptstring

modelstring

parametersobject

input_imagesobject

output_image_urlobject

output_image_widthobject

output_image_heightobject

output_image_sizeobject

created_atstring

Example

cURL
Python
Node.js
Go

curl "https://app.neuroflash.com/api/ds-prototypes/history/{image_id}" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID"

import requests

response = requests.get(
    f"https://app.neuroflash.com/api/ds-prototypes/history/{image_id}",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id},
).json()

const response = await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/history/${imageId}`,
  { headers: { Authorization: `Bearer ${token}`, "x-workspace-id": workspaceId } }
).then((r) => r.json());

req, _ := http.NewRequest("GET", "https://app.neuroflash.com/api/ds-prototypes/history/"+imageID+"", nil)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Response:

{
  "output_image_id": "string",
  "batch_id": "string",
  "user_id": 0,
  "workspace_id": "string",
  "prompt": "string",
  "model": "string",
  "parameters": {},
  "input_images": {},
  "output_image_url": {},
  "output_image_width": {},
  "output_image_height": {},
  "output_image_size": {},
  "created_at": "2024-01-15T10:30:00Z"
}

Delete Generation

DELETE/history/{image_id}

Delete a generation and its associated image from storage.

Args: image_id: The output image ID (generation ID) to delete

Returns: Success message

Path Parameters

Parameter	Type	Required	Description
`image_id`	string	Yes

Example

cURL
Python
Node.js
Go

curl -X DELETE "https://app.neuroflash.com/api/ds-prototypes/history/{image_id}" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "x-workspace-id: YOUR_WORKSPACE_ID"

import requests

requests.delete(
    f"https://app.neuroflash.com/api/ds-prototypes/history/{image_id}",
    headers={"Authorization": f"Bearer {token}", "x-workspace-id": workspace_id},
)

await fetch(
  `https://app.neuroflash.com/api/ds-prototypes/history/${imageId}`,
  {
    method: "DELETE",
    headers: { Authorization: `Bearer ${token}`, "x-workspace-id": workspaceId },
  }
);

req, _ := http.NewRequest("DELETE", "https://app.neuroflash.com/api/ds-prototypes/history/"+imageID+"", nil)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("x-workspace-id", workspaceID)

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

Response:

{}

Generate Text2Image​

Request Body​

Response​

Example​

Generate Image2Image​

Request Body​

Response​

Example​

Get Available Models​

Example​

Get Generation History​

Query Parameters​

Example​

Get Generation By Id​

Path Parameters​

Response​

Example​

Delete Generation​

Path Parameters​

Example​

Generate Text2Image

Request Body

Response

Example

Generate Image2Image

Request Body

Response

Example

Get Available Models

Example

Get Generation History

Query Parameters

Example

Get Generation By Id

Path Parameters

Response

Example

Delete Generation

Path Parameters

Example