ZoeDepth preprocessor.

Generate synced sounds for any video, and return it with its new sound track (like MMAudio)

Vidu Reference-to-Image creates images by using a reference images and combining them with a prompt.

ffmpeg utility to interleave videos

Interpolate images with RIFE - Real-Time Intermediate Flow Estimation

ltx-2.3-22b/audio-to-video/lora

Generate video with audio from audio, text and images using LTX-2.3 and custom LoRA

z-image/turbo/tiling/lora

Generate seamlessly tiling photorealistic images from text using Z-Image Turbo and custom LoRA

pixverse/v3.5/image-to-video/fast

Generate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast

wan-22-trainer/t2v-a14b

Train custom LoRAs for Wan-2.2 T2V/I2V 480P

MAGI-1 distilled extends videos faster with an exceptional understanding of physical interactions and prompts

bria/video/background-removal/realtime

Remove video backgrounds in real time with Bria’s VRMBG 3.0 model. Built for live streaming, real-time video apps, content creation, and low-latency workflows that need fast, accurate background removal.

Generate Images with ControlNet.

flux-general/rf-inversion

A general purpose endpoint for the FLUX.1 [dev] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.

pixverse/v3.5/text-to-video/fast

Generate high quality video clips quickly from text prompts using PixVerse v3.5 Fast

pixverse/v3.5/effects

Generate high quality video clips with different effects using PixVerse v3.5

pixverse/v4/text-to-video/fast

Generate high quality and fast video clips from text and image prompts using PixVerse v4 fast

qwen-image-edit-2509-lora-gallery/lighting-restoration

Removes harsh shadows and light spots from images, replacing them with soft, even, natural-looking illumination.

Place a person’s photo into iconic cities worldwide.

ideogram/v2a/remix

Create variations of existing images with Ideogram V2A Remix while maintaining creative control through prompt guidance.

Apply diverse photography styles and effects to transform your images.

bria/embed-product

Seamlessly embed products into any scene with pixel-perfect control, automatic perspective, and natural lighting. Trained on licensed data - risk-free for advertising and eCommerce production.

Transform objects with different surface textures like marble, wood, or fabric.

LoRA trainer for ERNIE-Image, Baidu's powerful 8B-parameter text-to-image model.

Adjust color temperature, brightness, contrast, saturation, and gamma values for color correction.

Train LoRA adapters for TRELLIS.2 model

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.

wan/v2.2-5b/text-to-video/distill

Wan 2.2's 5B distill model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding

Generate long videos from images using LongCat Video