Search models...Search by model, task, category and more

LoRA endpoint for the Qwen Image Edit 2509 model.

Moondream2 is a highly efficient open-source vision language model that combines powerful image understanding capabilities with a remarkably small footprint.

Generate 3D models from a single image with Hi3D.

Fine-tune FLUX 3 Image Klein on before/after image pairs to teach it a custom edit, with up to 10 input images per pair.

Stable Audio 3 Medium audio outpainting is a 1.4 billion parameter latent diffusion model that extends existing stereo audio beyond its original endpoint via causal continuation guided by text prompts.
![Image-to-image editing with FLUX.2 [klein] 4B from Black Forest Labs and custom LoRA. Precise modifications using natural language descriptions and hex color control.](https://v3b.fal.media/files/b/0a928e1f/c62zNs4MhBXgm-5w7n0C5_90bad8837ecc451e96f91da93b78f564.jpg)
Image-to-image editing with FLUX.2 [klein] 4B from Black Forest Labs and custom LoRA. Precise modifications using natural language descriptions and hex color control.

Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step

Automatically retouches faces to smooth skin and remove blemishes.

Wan 2.6 text-to-image model.

Train a MiniMax H3 LoRA with reference conditioning, so different modalities animate into video with audio; captions optional.

Generates vector images that hold a consistent style, from either a saved style ID or reference images attached directly.

Image colorization and color-grading model. Bring color to black-and-white photos or apply curated color treatments using simple style-based commands.

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Generates raster images that hold a consistent style, from either a saved style ID or reference images attached directly.

Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.

Virtual clothing try-on (2 images: person + garment)

Vidu's latest Q3 Reference to Video Mix model

Vidu's Q3 Turbo Model.

Writes song lyrics and a title from a text prompt describing a topic, theme, or song concept.

Remove background from videos filmed using chromakey, with automatic green spill suppression for clean, professional edges.

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks

Photo restoration model that automatically denoises, deblurs, and enhances old or damaged photos - removes imperfections while preserving original character.

Use the capabilities of the hunyuan foley model to bring life to your videos by adding sound effect to them.