Trending

minimax/h3-max/styles/hand-drawn

Generates 768p video with audio in a hand-drawn animation style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.

Clone voice of any person and speak anything in their voice using zonos' voice cloning.

ideogram/v2/turbo

Accelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.

z-image/turbo/inpaint/lora

Generate images from text, an image, a mask and custom LoRA using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

minimax/h3-max/styles/vhs

Generates 768p VHS-style video with audio from text prompts or an optional first-frame image. Supports 5–15 second clips and adjustable tape damage, from subtle analog noise to strong tracking distortion.

A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.

Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.

qwen-image-edit-plus-lora-gallery/integrate-product

Blend products into backgrounds with automatic perspective and lighting correction

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.

M-LSD line segment detection preprocessor.

Pixelcut's Background Remover produces fast, high-quality cutouts built for e-commerce product imagery

flux/srpo/image-to-image

FLUX.1 SRPO [dev] is a 12 billion parameter flow transformer that generates high-quality images from text with incredible aesthetics. It is suitable for personal and commercial use.

qwen-image-edit-2509-lora

LoRA endpoint for the Qwen Image Edit 2509 model.

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

Enhance facial features with professional retouching while maintaining a natural, realistic look

Stable Audio 3 Small SFX audio-to-audio is a 459 million parameter latent diffusion model that transforms input audio into new sound-effect variations guided by text prompts.

Generate professional product photography with realistic lighting and backgrounds.

flux-lora-canny

Utilize Flux.1 [dev] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.

Use the amazing capabilities of hunyuan image 2.1 to generate images that express the feelings of your text.

ltx-2.3-quality/extend-video

Extend high-quality video with audio from input video using LTX-2.3

Kandinsky 5.0 Pro is a diffusion model for fast, high-quality image-to-video generation.

Generate videos from prompts using CogVideoX-5B

Generate 3D models from one or more images using ReconViaGen 0.5

luma-photon/modify

Edit images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.