Send your API key on REST requests and from the CLI.
Text-to-image and image-to-image with Flux and other models.
Generate images with your trained LoRA models.
Turn a photo into cartoon or character styles.
Place a product image onto a background scene with a text prompt.
Text-to-video, image-to-video, and reference-based video models.
Animate a still image using motion from a reference video.
Text-to-speech, voice conversion, isolation, dubbing, and sound effects.
Chat-style text generation with OpenAI-compatible messages.
Get a text description of an image with a vision model.
Check when a generation has finished and get the output URL.