Model Browser
AI generation models on LORY
Browse 60 models across image, video, audio, and 3D — from OpenAI, Google, ElevenLabs, Bytedance, Alibaba and more. Pick one to learn what it does best, then try it in your own story project.
Image models
27 models available
Seedream 5 Lite – Composite
Bytedance Seedream 5 Lite multi-reference composition — accepts up to 10 reference images and blends them via prompt-led restyling, with Figure 1 /…
Seedream 5 Lite – Edit
Bytedance Seedream 5 Lite single-image edit profile — prompt-led transformation with preserved composition and framing. Best for end-state edits ("change…
OpenAI gpt-image-2 – Composite
gpt-image-2 composite profile that blends up to 10 high-fidelity references into a single cohesive scene.
OpenAI gpt-image-2 – Edit
gpt-image-2 edit profile with automatic high-fidelity input processing for detailed, identity-aware edits.
OpenAI gpt-image-2 – Generate
Latest OpenAI text-to-image model with stronger prompt adherence, improved text rendering, and flexible sizes.
OpenAI gpt-image-2 – Inpaint
gpt-image-2 mask-based inpainting for surgical replacements with strong scene and lighting continuity.
Video models
20 models available
Happy Horse 1.0 Reference to Video
Alibaba Happy Horse 1.0 reference-to-video model with 1-9 ordered reference images, native synchronized audio, and 3-15s clips at 720p or 1080p.
Veo 3.1 Lite (First/Last Frame)
Veo 3.1 Lite first/last-frame model for short 8s motion transitions with native audio and 720p/1080p output.
Veo 3.1 Lite (Image to Video)
Veo 3.1 Lite image-to-video profile for short 4-8s clips with prompt-led motion and optional native audio.
LTX-2.3 Fast (Image to Video)
LTX-2.3 Fast i2v with native audio, up to 20s duration, 4K resolution, and start+end frame transitions.
LTX-2.3 Pro (Image to Video)
LTX-2.3 Pro i2v: higher fidelity with better motion stability and visual detail. Up to 10s, 4K, native audio. Best for final renders.
Vidu Q3 (Image to Video)
Vidu Q3 image-to-video profile for broad stylistic range and rapid experimentation.
Audio models
10 models available
ElevenLabs Music
ElevenLabs Eleven Music (music_v1) — full-track music generation direct from ElevenLabs with vocal or instrumental output, multilingual singing, and 44.1…
Minimax Music 2.6
Full-track music generator with structured lyrics support — vocal or instrumental, configurable sample rate/format/bitrate, and lyric structure tags…
Stable Audio 2.5 (Audio-to-Audio)
Audio-to-audio transformation model — restyle a source clip with a target-sound prompt and a strength slider to balance source preservation vs. prompt…
ElevenLabs v3 (TTS)
ElevenLabs v3 direct — the most expressive TTS model for cinematic trailers, dramatic narration, and emotional dialogue.
Sonauto v2 (Text-to-Music)
Music generation model optimized for prompt-driven song ideas with strong style control.
ElevenLabs Multilingual v2 (TTS)
High-quality multilingual TTS suited for polished narration and character voice lines.
3D Model models
3 models available
Meshy v6 Image to 3D
Image-to-3D model suited for detailed object reconstruction with export-ready meshes.
Tripo v2.5 Image to 3D
Single-image to 3D model for fast concept meshes and textured asset generation.
Tripo v2.5 Multiview to 3D
Multi-view to 3D model that improves geometry stability from multiple reference angles.