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

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

Generate high-quality videos with UGC-like avatars from audio
![Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.](https://storage.googleapis.com/fal_cdn/fal/Upscale-5.jpeg)
Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
![FLUX1.1 [pro] ultra fine-tuned is the newest version of FLUX1.1 [pro] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.](https://storage.googleapis.com/falserverless/gallery/flux-pro-11-ultra.webp)
FLUX1.1 [pro] ultra fine-tuned is the newest version of FLUX1.1 [pro] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.

Change a video’s lighting using a relit reference frame while preserving the scene, subjects, and original performance. ID-V2V Relight propagates the new illumination across the video.
Automatically generates text captions for your videos from the audio as per text colour/font specifications

Stable Audio 3 Small Music Base is the foundational 459 million parameter checkpoint generating full music compositions up to 2 minutes from text prompts, intended as the unmodified base for fine-tuning.

Use the capabilities of lightx to relight and recamera your videos.

Generate high quality video clips with different effects using PixVerse v4

Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transforer which features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.

Generate professional product photography with realistic lighting and backgrounds.

Leffa Virtual TryOn is a high quality image based Try-On endpoint which can be used for commercial try on.

Generate long videos in 720p/30fps from text using LongCat Video

FLUX.3 is Black Forest Labs' frontier audio/video model. Re-render a previously generated draft at full quality — same seed, same motion, no re-planning.

LongCat image is a 6B parameter model excelling at multilingual text rendering, photorealism and deployment efficiency.

Finegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.

Train a MiniMax H3 LoRA on your own captioned clips for pure text-to-video generation with matching audio.

An efficent SDXL multi-controlnet image-to-image model.

A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.

High-quality text-to-image model by Baidu. Supports English, Chinese, and Japanese prompts with built-in prompt expansion.

Generates 768p video with audio in a 16-bit pixel-art style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.

Holistically-Nested Edge Detection (HED) preprocessor.

Marlin is a 2B video VLM tuned for the two questions developers actually want to ask of their videos: what is happening, and when?

Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.