API docs / Text models

clip-interrogator API

Analyzes images to generate optimized text prompts that describe them, combining OpenAI's CLIP and Salesforce's BLIP models. Takes an image as input and outputs a detailed text prompt that can be used with text-to-image models like Stable Diffusion to recreate similar images. Tests the input image against various artists, mediums, and styles to understand how different models perceive the content, then combines these results with BLIP captioning to create comprehensive prompts for art generation.

Model id
pharmapsychotic/clip-interrogator
Provider
pharmapsychotic
Output
Text
Price
From 1 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "pharmapsychotic/clip-interrogator". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "pharmapsychotic/clip-interrogator",
  "input": {
    "reference_images": [
      "https://example.com/input.png"
    ]
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
reference_imagesrequiredarray of URLs

Input image

Up to 1 files · Accepts image/*

clip_model_namestring

Default: ViT-L-14/openai

One of: ViT-L-14/openai, ViT-H-14/laion2b_s32b_b79k, ViT-bigG-14/laion2b_s39b_b160k

modestring

Default: best

One of: best, classic, fast, negative