Trending

Meshy-6 is the latest model from Meshy. It generates realistic and production ready 3D models.

ideogram/custom-models/generate

Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours

ideogram/custom-models

Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours

Lyra 2.0 is an image-to-video model that turns a single image into an explorable 3D-style video with camera-controlled motion.

Audio-driven talking avatar generation powered by the SoulX-FlashTalk 14B model.

All-in-one image AI with JoyAI-Image. Understand, create, and edit images through natural language—the model's deep visual understanding powers more accurate generation and precise editing in a unified system.

Physics-based video generation with Goal Force. Point where you want objects to move, set force direction and strength, get physically plausible results.

sora-2/characters

Generate character ids to use with Sora 2 generations

High-quality voice cloning TTS model that generates 48kHz speech from text and a reference audio. Distilled to 4 steps for fast inference.

Physics-aware image editing with PhysicEdit. Make realistic edits that follow real-world physics—handles complex effects like refraction, material changes, and deformation with physically plausible results.

Convert your assets into lottie using Omnilottie.

Convert your assets into lottie using Omnilottie.

Convert your assets into lottie using Omnilottie.

OneReward is a finetuned version of Flux 1.0 Fill with intelligent editing capabilities.

qwen-image-2/pro/text-to-image

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

qwen-image-2/text-to-image

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

qwen-image-2/pro/edit

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

qwen-image-2/edit

Qwen-Image-2.0 is a next-generation foundational unified generation-and-editing model

MultiShotMaster is a controllable multi-shot narrative video generation framework that supports text-driven inter-shot consistency, variable shot counts and shot durations, customized subject with motion control, and background-driven customized scene.

Generate video from text and videos using NVIDIA's 2B Cosmos Distilled Model

Generate video from text and videos using NVIDIA's 2B Cosmos Post-Trained Model

Generate video from text and images using NVIDIA's 2B Cosmos Post-Trained Model

Generate video from text using NVIDIA's 2B Cosmos Post-Trained Model

decart/lucy-i2v

Lucy delivers lightning fast performance that redefines what's possible with image to video AI