LongCat-Video-Avatar is an audio-driven video generation model that can generates super-realistic, lip-synchronized long video generation with natural dynamics and consistent identity.

M-LSD line segment detection preprocessor.

ltx-2-19b/extend-video

Extend video with audio using LTX-2

Sana v1.5 1.6B is a lightweight text-to-image model that delivers 4K image generation with impressive efficiency.

Search any video with a text prompt - Scene Finder locates the matching moments and returns their time segments and extracted frames.

Default parameters with automated optimizations and quality improvements.

Convert your assets into lottie using Omnilottie.

flux-1/dev/redux

FLUX.1 [dev] Redux is a high-performance endpoint for the FLUX.1 [dev] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.

qwen-image-edit-2509-lora-gallery/remove-element

Remove unwanted elements (objects, people, text) while maintaining image consistency

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

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

Convert your assets into lottie using Omnilottie.

bria/fibo-lite/generate/structured_prompt

Convert plain text into Fibo-Lite's transparent JSON-structured prompts - Bria's unique controllability layer that no closed model offers. Built for agentic and enterprise workflows.

ltx-video-13b-distilled/extend

Extend videos using LTX Video-0.9.7 13B Distilled and custom LoRA

flux-2-trainer/edit

Fine-tune FLUX.2 [dev] from Black Forest Labs with custom datasets. Create specialized LoRA adaptations for specific editing tasks.

heygen/avatar3/digital-twin

Heygen Avatar V3 Model for Digital Twin

MAGI-1 distilled is a faster video generation model with exceptional understanding of physical interactions and cinematic prompts

pixverse/v4.5/image-to-video/fast

Generate fast high quality video clips from text and image prompts using PixVerse v4.5

bria/reimagine

Structure Reference allows generating new images while preserving the structure of an input image, guided by text prompts. Perfect for transforming sketches, illustrations, or photos into new illustrations. Trained exclusively on licensed data for safe and risk-free commercial use.

pixverse/v3.5/text-to-video

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

bria/video/erase/prompt

Erase unwanted objects, people, or elements from video with a text prompt. High-fidelity output with strong temporal consistency, trained on licensed data for safe commercial use.

Transform your photos into wojak style while keeping the original characters likeness

pixverse/extend/fast

PixVerse Extend model is a video extending tool for your videos using with high-quality video extending techniques

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

bria/fibo-edit/erase_by_text

Remove unwanted objects from images with a text prompt - fast, precise editing that seamlessly blends results. Built for production scale and trained on licensed data for safe commercial use.

Place your subject in any scene you imagine, from enchanted forests to urban settings, with professional composition and lighting

wan-22-trainer/i2v-a14b

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

Nemotron-Labs-Diffusion-VLM-8B is the vision-language extension of the Nemotron-Labs-Diffusion family.