Generate Image And Caption
A 2-step recipe with NVIDIA NIM. We can help you get access.
Recipe · 2 steps
Generate Image And Caption
with NVIDIA NIM · Artificial Intelligence Management
Generate an image, then describe it with a VLM to produce a caption.
- Generate an image from the text prompt with the selected publisher/model visual generative NIM.
- Caption the freshly generated image by passing its base64 artifact as a data-URI image_url into a vision-language model.
What you'll need to have ready
- apiKey: NVIDIA developer API key (nvapi-...) sent as a Bearer token.
- publisher: Image model publisher path segment (e.g. black-forest-labs).
- model: Image model slug path segment (e.g. flux.1-schnell).
- prompt: Text prompt describing the image to generate.
- visionModel: Vision-language model id used to caption the generated image.
For your developer
Arazzo workflow nvidia-nim:generate-image-and-caption, 2 operations: generateImage → createVisionChatCompletion. Specs on APIs.io.