Model Browser
AI generation models on LORY
Browse 66 models across image, video, audio, and 3D — from OpenAI, Google, ElevenLabs, Bytedance, Alibaba and more, including GPT Image 2.5 Flare and MiniMax H3 Max – Image to Video. Pick one to learn what it does best, then try it in your own story project.
Try LORY free — no subscription
Start with free welcome credits — we never ask for payment info during your trial. Pay only when you decide to top up after your credits run out.
Image models
29 models available
GPT Image 2.5 Flare
Fast OpenAI image model with sharp, readable in-image text and true transparent-background cutouts.
Seedream 5.0 Pro
ByteDance's flagship text-to-image model — photographic realism at 2K and dependable rendered text in many languages.
Seedream 5.0 Lite – Composite
ByteDance Seedream 5.0 Lite multi-reference composition — blends up to 10 references with prompt-led restyling.
Seedream 5.0 Lite – Edit
ByteDance Seedream 5.0 Lite single-image editing — prompt-led transformation with preserved composition.
GPT Image 2 – Composite
Blend multiple reference images into a single cohesive scene with GPT Image 2. Inputs are processed at high fidelity.
GPT Image 2 – Edit
Edit an image with GPT Image 2. Input images are processed at high fidelity for detailed, identity-aware revisions.
Video models
25 models available
MiniMax H3 Max – Image to Video
Top-ranked image-to-video model with native audio, first and last frame control, and strong prompt adherence.
Wan 3.0 – Image to Video
Turn a still frame into a finished shot with synced audio, anywhere from 2 to 30 seconds. It holds motion and identity well across longer takes, and an optional end frame lets you decide where the shot lands.
Voice Text Overlay
Turn a voice clip's transcript into a transparent text overlay timed to the spoken words. Useful for subtitles, lyric-style captions, and on-screen dialogue treatments you want to place over other footage.
Image Animation
Turn a still image into a moving shot with a chosen camera move. Useful for storyboard frames, concept stills, and reference images when you want simple motion from one image.
Grok Imagine – Reference to Video
Build a single video shot from several reference images with Grok Imagine. It is a strong choice when you want to combine subject, setting, and style references in one clip, with synced audio included.
HappyHorse-1.0 – Reference to Video
Shape a single video shot from several reference images with Happy Horse 1.0. It works well when you want tighter control over characters, styling, or scene details while still generating one finished clip with synced audio.
Audio models
9 models available
ElevenLabs Music
ElevenLabs Eleven Music (music_v1) — full-track music generation with vocals or instrumental, multilingual singing, and 44.1 kHz studio-quality output.
MiniMax Music 2.6
Full-track music generation with optional structured lyrics, vocal or instrumental output, and configurable audio settings.
Stable Audio 2.5 – Audio to Audio
Audio-to-audio transformation with prompt-driven restyling and a strength control to preserve or replace the source.
Eleven v3 – Text to Speech
ElevenLabs' most expressive TTS model — cinematic delivery, emotional range, and dramatic pacing. Ideal for trailers, narration, and character dialogue.
Eleven Multilingual v2 – Text to Speech
High-quality multilingual text-to-speech by ElevenLabs with 21 preset voices, style control, and speed adjustment.
ACE-Step – Text to Audio
Text-to-audio generations with optional structured lyrics and genre tags.
3D Model models
3 models available
Meshy v6 – Image to 3D
Generate a 3D model from a single image using Meshy v6. Supports PBR, quad/triangle topology, and optional texture prompts.
Tripo v2.5 – Multiview to 3D
Generate high-quality 3D models from multi-view images (front, left, back, right)