Yollomi - Image and Video Generation
Generates images and videos via the Yollomi API with support for multiple AI models including Flux, DALL-E, Stable Diffusion, and video generation models. Features unified endpoint with flexible modelId parameters for diverse creative tasks like image editing, background removal, face swapping, and
🚀 Yollomi is an AI-powered image and video generation platform that creates stunning visuals from text prompts. With a single unified API, you can generate images using models like Flux and Stable Diffusion, or create videos with Kling and Sora. Simply provide your API key, choose a model, and get creative—supporting multiple aspect ratios and customizable parameters.
💡 Perfect for content creators, designers, and developers who need quick visual assets. Use cases include generating marketing images, removing backgrounds, swapping faces, upscaling photos, restoring old pictures, and creating short videos. Each generation consumes credits based on the model complexity.
✨ One endpoint powers everything—images, videos, and advanced editing tools like object removal and virtual try-on. No complex integrations needed; just authenticate and start creating.
Requirements
API key for Yollomi authentication (required)