AI Models
Model families, fully indexed.
This catalog reflects the live model registries wired into ELYSIO right now. Browse by family first, then scan, filter, and compare any bound model route with its provider, access profile, and related tool surfaces intact.
Total models
132
Families
4
Providers
22
Catalog scope
Video, image, voice, and world families are all listed from the same routed catalog used by the public tools and studio surfaces. The layout is intentionally split so the summary reads quickly before the full index starts.
Video Models
43 routed models
9 providers routed into this family.
Browse 43 routed video models currently wired into ELYSIO Video Studio.
Family
Video Models
Coverage
43 / 132
fal.ai leads with 23 routes
2 access modes, led by Native
Primary profile: 1.2x credits
Image Models
33 routed models
10 providers routed into this family.
Browse 33 image generation and edit-capable models available in the image lane.
Family
Image Models
Coverage
33 / 132
OpenArt Collection leads with 13 routes
2 access modes, led by Profile
Primary profile: 1.18x credits
Voice Models
14 routed models
6 providers routed into this family.
Browse 14 speech, narration, and audio-ready models connected to the voice workspace.
Family
Voice Models
Coverage
14 / 132
OpenArt Collection leads with 7 routes
2 access modes, led by Balanced
Primary profile: Audio routed
World Models
42 routed models
1 provider routed into this family.
Browse 42 world and 3D model bindings currently cataloged for immersive production.
Family
World Models
Coverage
42 / 132
fal.ai leads with 42 routes
2 access modes, led by Pro+
Primary profile: image-to-3d
Catalog Filters
Scan the stack without opening every family.
Family
Provider
Access
Profile
Showing the heaviest profile labels first. Expand the filter when you need a smaller route profile.
Sort families
Family Rail
Jump to the family you need.
The visible families below are already ordered by the current sort mode. Use this rail to jump directly into the matching section instead of scanning the full page.
Video Models
43
routes · 9 providers
fal.ai currently carries the heaviest share.
World Models
42
routes · 1 provider
fal.ai currently carries the heaviest share.
Image Models
33
routes · 10 providers
OpenArt Collection currently carries the heaviest share.
Voice Models
14
routes · 6 providers
OpenArt Collection currently carries the heaviest share.
Family Compare
Compare the stack before opening a family.
This readout shows which family is broadest, who leads each catalog, and how access or pricing profiles cluster before you drill into individual routes.
Video Models
43
routed models
World Models
42
routed models
Image Models
33
routed models
Voice Models
14
routed models
Video Models
Browse 43 routed video models currently wired into ELYSIO Video Studio.
43
routes
fal.ai
23 routes
Native
28 routes
1.2x credits
18 profiles
9
providers
World Models
Browse 42 world and 3D model bindings currently cataloged for immersive production.
42
routes
fal.ai
42 routes
Pro+
33 routes
image-to-3d
4 profiles
1
providers
Image Models
Browse 33 image generation and edit-capable models available in the image lane.
33
routes
OpenArt Collection
13 routes
Profile
20 routes
1.18x credits
17 profiles
10
providers
Voice Models
Browse 14 speech, narration, and audio-ready models connected to the voice workspace.
14
routes
OpenArt Collection
7 routes
Balanced
12 routes
Audio routed
1 profile
6
providers
Video Models
Video Models
Browse 43 routed video models currently wired into ELYSIO Video Studio.
Provider mix
Access mix
Profile mix
Lead Provider
fal.ai
23 of 43 routes currently resolve here.
Primary Access
Native
28 routes share this access posture across the family.
Primary Profile
1.2x credits
18 total profile labels are active in this family.
Stable and high-quality baseline for production video generation.
Low-cost FAI.ai starter profile for quick story blocking and testing motion direction.
FAI.ai flagship direction profile for premium narrative pacing and cinematic control.
FAI.ai motion profile tuned for kinetic action, subject tracking, and punchier performance.
FAI.ai storytelling profile aimed at scene-to-scene coherence and ad-ready polish.
FAI.ai performance profile for expressive character shots and dialogue-driven motion.
Advanced cinematic motion profile with richer detail targeting.
Smooth choreography and dance-style movement profile.
High-fidelity cinematic motion model for hero shots and ad-grade visuals.
Faster runway generation profile for iterative creative production.
Experimental runway model profile for stylized narrative sequences.
Crisp visual detail profile with strong action composition.
Native fal.ai Kling O3 Standard binding for text-to-video, image-to-video, and structured video edits.
Native fal.ai Kling O3 Pro binding for premium text-to-video, image-guided motion, reference-led video generation, and high-end video edits.
Native fal.ai Kling V3 motion-control binding for matching a subject image to a motion reference clip.
Native fal.ai Kling V3 Pro motion-control binding for higher-fidelity subject motion transfer and premium performance control.
Native fal.ai LTX 2.3 Fast binding for fast text-to-video and image-to-video ideation with optional end-frame transitions.
Native fal.ai LTX 2.3 binding for higher-end text-to-video and image-to-video generation with structured start/end frame transitions.
Native fal.ai LTX 2.3 extend binding for continuing an existing clip with coherent next-shot motion.
Native fal.ai LTX 2.3 retake binding for targeted section rewrites of an existing clip with new edit direction.
Native fal.ai Veo 3.1 first/last-frame binding for controlled transitions between a starting frame and a closing frame.
Native fal.ai Veo 3.1 Fast first/last-frame binding for lower-latency transition planning between two anchor frames.
Native fal.ai Veo 3.1 Fast binding for faster text-to-video and image-to-video generation with Veo-class motion quality.
Native fal.ai Veo 3.1 binding for premium text-to-video, image-to-video, and reference-led generation.
Native fal.ai Veo 3.1 Fast extend binding for quickly continuing an existing clip with coherent follow-through motion.
Native fal.ai Veo 3.1 extend binding for premium continuation of an existing clip with stronger temporal coherence.
Native fal.ai Lucy 5B binding for image-to-video generation with a lighter-weight Lucy family endpoint.
Native Decart Lucy Edit Fast binding on fal.ai for rapid instruction-led video edits on existing clips.
Native Decart Lucy Edit Dev binding on fal.ai for higher-control experimental video edits and revision passes.
Native Decart Lucy Edit Pro binding on fal.ai for premium instruction-led video editing and shot revision.
Native Decart Lucy Restyle binding on fal.ai for stylistic transfer and visual reinterpretation of existing clips.
Native fal.ai LTX 2.3 binding for audio-driven video generation with optional first-frame image control.
Native fal.ai LTX 2 binding for audio-to-video generation using speech or music as the primary timing source.
Native fal.ai LongCat single-avatar binding for image-plus-audio talking-head video generation.
Native fal.ai LongCat single-avatar binding for audio-driven avatar video generation without a required starting image.
Stylized storytelling profile tuned for social-friendly edits.
Fast-paced motion profile suitable for short-form content.
Atmospheric realism profile with soft cinematic grading.
Balanced profile for narrative scenes and controlled motion.
Hyper-realistic physics and extended duration video generation.
High-speed, high-quality motion and 3D environment generation.
Stylized animation and rapid iterative motion editing.
Creative visual effects and complex scene transformations.
World Models
World Models
Browse 42 world and 3D model bindings currently cataloged for immersive production.
Provider mix
Access mix
Profile mix
Lead Provider
fal.ai
42 of 42 routes currently resolve here.
Primary Access
Pro+
33 routes share this access posture across the family.
Primary Profile
image-to-3d
4 total profile labels are active in this family.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for 3d-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for world workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for image-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
World generation lane for text-to-3d workflows inside the immersive production stack.
Image Models
Image Models
Browse 33 image generation and edit-capable models available in the image lane.
Provider mix
Access mix
Profile mix
Lead Provider
OpenArt Collection
13 of 33 routes currently resolve here.
Primary Access
Profile
20 routes share this access posture across the family.
Primary Profile
1.18x credits
17 total profile labels are active in this family.
Fast and reliable general-purpose image generation.
Native fal.ai Nano Banana 2 binding for fast social visuals and prompt-faithful concept polish.
Premium Google Nano Banana Pro binding on fal.ai for higher-end concept generation and prompt-faithful commercial edits.
Native fal.ai Seedream V4.5 binding for modern editorial generation and fast reference-led edits.
Native fal.ai FLUX 2 Pro binding for premium prompt fidelity, rich detail, and structured image editing.
Native fal.ai FLUX 2 Klein 4B binding for faster ideation, layout exploration, and lightweight structured edits.
Native fal.ai FLUX 2 Klein 9B binding for richer detail, stronger prompt adherence, and reference-aware image edits.
Native fal.ai FLUX 2 Flex binding for general-purpose generation plus reference-aware image edits on the same family.
Native fal.ai Qwen Image 2 binding for prompt-heavy illustration, editorial generation, and reference-guided image edits.
Native fal.ai Qwen Image 2 Pro binding for premium prompt fidelity, dense infographic-style layouts, and higher-end edits.
Native fal.ai GPT Image 1.5 binding for strong prompt adherence, design-oriented generation, and image edits.
Native fal.ai FireRed binding for instruction-led image edits, object replacement, and heavy visual transformation on existing source images.
FAI.ai portrait profile for clean commercial realism and premium skin detail.
FAI.ai campaign profile for product, packaging, and brand launch shots.
FAI.ai visual-development profile tuned for narrative beats and consistent scene planning.
Fashion-forward generation profile optimized for fit-check and editorial looks.
High-detail cinematic realism with dramatic lighting.
Balanced realism and artistic interpretation for hero visuals.
Fast concept generation profile for rapid ideation.
Bold creative concept art and visual storytelling style.
Photorealistic outputs with natural texture and skin detail.
Large-scale diffusion style for strong detail and composition.
Clean anime lines, dynamic poses, and vibrant stylization.
Family-friendly stylized 3D toon aesthetic.
Commercial-grade realistic product and people renders.
Texture-rich visuals optimized for depth and material feel.
Highly coherent and prompt-accurate generation from OpenAI.
State-of-the-art artistic and photorealistic generation.
Specialized anime and illustration aesthetic.
Next-generation open-weights image model with strong text rendering.
High-quality stylized and gaming asset generation.
Premium anime and character generation.
Unparalleled text rendering in images and typography.
Voice Models
Voice Models
Browse 14 speech, narration, and audio-ready models connected to the voice workspace.
Provider mix
Access mix
Profile mix
Lead Provider
OpenArt Collection
7 of 14 routes currently resolve here.
Primary Access
Balanced
12 routes share this access posture across the family.
Primary Profile
Audio routed
1 total profile labels are active in this family.
General-purpose text-to-speech profile.
Lower-latency profile for quick previews and drafts.
Natural vocal expression profile with rich tone.
Balanced profile for clean and expressive spoken audio.
Conversational profile optimized for short-form narration.
Experimental profile for multimodal voice quality tests.
FAI.ai starter voice profile for fast guided narration and drafts.
FAI.ai narration profile focused on polished long-form delivery and premium pacing.
FAI.ai premium dubbing profile for rapid line-by-line scene performance.
Creative voice experimentation profile.
High definition narration profile from OpenAI.
Hyper-realistic voice cloning and expressive speech generation.
Full-song generation with rich vocal and instrumental composition.
High-fidelity AI music generation with fine-grained segment control.