Explore AI models on Synexa — 70 models, one API

Google's state of the art image generation and editing model 🍌🍌

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

4-step distilled version of FLUX.2 [klein], a 9B foundation image model offering maximum flexibility and control for fast text-to-image and image-to-image generation.

Google's state of the art image generation and editing model 🍌🍌

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language

Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.

4-step distilled version of FLUX.2 [klein], a 9B foundation image model offering maximum flexibility and control for fast text-to-image and image-to-image generation.

OpenAI's state-of-the-art image generation model. Create and edit images from text with strong instruction following, sharp text rendering, and detailed editing.

Qwen's image editing model with multi-image editing, identity preservation, and ControlNet support for precise text, people, and product editing.

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

Kling 3.0 motion control: transfer motion from a reference video to any character image with improved consistency and quality.

ByteDance's advanced video generation model with native audio, keyframe control, and multimodal references for consistent character and style.

Generate 5s 480p videos using Wan 2.2 14B. A comprehensive video foundation models that pushes the boundaries of video generation.

Avatar 4 turns a photo into a talking avatar that speaks your text or lip-syncs to an audio file.

Fabric 1.0 turns a photo plus an audio track into a talking-head video.

Add sound to video using the MMAudio V2 model. An advanced AI model that synthesizes high-quality audio from video content, enabling seamless video-to-audio transformation.

Suno v5.5 generates full-length, high-fidelity AI songs with vocals and instrumentation from a single text prompt, producing 44.1 kHz stereo MP3 output.

ACE-Step generates music with sung lyrics from a list of genre tags, extremely cheaply.

Kokoro is a lightweight American-English text-to-speech model that is fast and very cheap to run.

Lyria 2 generates 30 seconds of 48kHz music from a descriptive text prompt.

Xiaomi MiMo V2.5 text-to-speech. Speaks text with one of 9 built-in voices, clones a voice from a reference clip, or invents a new voice from a written description.

AuraSR upscales images 4x with a GAN-based model that is fast and consistent.

Clarity Upscaler enlarges images while adding believable detail, guided by an optional prompt.

Robust face restoration algorithm for old photos / AI-generated faces

Crisp Upscale raises an image's resolution while sharpening small details and edges.

Practical face restoration algorithm for *old photos* or *AI-generated faces*

Professional-grade image upscaling. Increase image resolution up to 4x with adjustable creativity and resemblance controls.

Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets

State-of-the-art single-image to 3D object generation. Produces production-ready GLB meshes with PBR textures in under a second.

Generate high-quality 3D models with accurate geometry and realistic textures from input images.

Advanced AI-powered 3D model generator that transforms images into production-ready 3D assets with high-quality textures and multiple export formats including GLB, FBX, USDZ, and OBJ.

TRELLIS.2 is a state-of-the-art 4B parameter 3D generative model for high-fidelity image-to-3D generation with complex topologies, sharp features, and full PBR materials.

TRELLIS converts a single image into a textured 3D mesh.