Media Model Library
Creative models, mapped to the work they do.
Browse image, video, and audio model families together with the endpoints and tasks recorded in Ethen's media catalog.
Catalog
Every family, every endpoint.
Search and filter the families by name, modality, or task, then open a family to see its exact cataloged endpoints — each with its task, catalog status, and schema state.
Source: Studio canonical catalog studio-fal-catalog-v2, sha 333e0a2021b1, Studio commit c8ef436831e2. Delivery for every family listed is fal.ai.
492 of 492 families
- video30 endpointsKling VideoThirty-endpoint Kling video suite spanning LipSync dubbing, O1 dual-keyframe, O3 4K, and standard tiers.Image to VideoReference to VideoSpeech+3Licence not stated · 30 schemas
- video30 endpointsMiniMaxHailuo 02 video generation to 10s 1080p with director camera, plus Video-01 live and speech endpoints.Image GenerationImage to VideoSpeech+2Licence not stated · 30 schemas
- image23 endpointsImage EditingImage GenerationLicence not stated · 23 schemas
- video22 endpointsLTX 2.3 22BImage to VideoLoRA TrainingText to Video+2Licence not stated · 22 schemas
- video21 endpointsViduVidu Q1 and Q2 video lines with 2-8s duration control, plus reference-to-image and text-to-image endpoints.Image GenerationImage to VideoReference to Video+3Licence not stated · 21 schemas
- video20 endpointsLTX 2 19BImage to VideoLoRA TrainingText to Video+2Licence not stated · 20 schemas
20 eligible. Cataloged is not executable: Studio resolves which endpoints a project can run.
Endpoint Task Catalog status Schema fal-ai/ltx-2-19b/audio-to-videovideo editing Eligible Schema available · 26 fields · requires prompt, audio_url fal-ai/ltx-2-19b/audio-to-video/loralora training Eligible Schema available · 27 fields · requires loras, prompt, audio_url fal-ai/ltx-2-19b/distilled/audio-to-videovideo editing Eligible Schema available · 24 fields · requires prompt, audio_url fal-ai/ltx-2-19b/distilled/audio-to-video/loralora training Eligible Schema available · 25 fields · requires loras, prompt, audio_url fal-ai/ltx-2-19b/distilled/extend-videovideo editing Eligible Schema available · 25 fields · requires prompt, video_url fal-ai/ltx-2-19b/distilled/extend-video/loralora training Eligible Schema available · 26 fields · requires loras, prompt, video_url fal-ai/ltx-2-19b/distilled/image-to-videoimage to video Eligible Schema available · 22 fields · requires prompt, image_url fal-ai/ltx-2-19b/distilled/image-to-video/loraimage to video Eligible Schema available · 23 fields · requires loras, prompt, image_url fal-ai/ltx-2-19b/distilled/text-to-videotext to video Eligible Schema available · 17 fields · requires prompt fal-ai/ltx-2-19b/distilled/text-to-video/loratext to video Eligible Schema available · 18 fields · requires loras, prompt fal-ai/ltx-2-19b/distilled/video-to-videovideo to video Eligible Schema available · 30 fields · requires prompt, video_url fal-ai/ltx-2-19b/distilled/video-to-video/loravideo to video Eligible Schema available · 31 fields · requires loras, prompt, video_url - image18 endpointsImage Apps V2Image EditingImage GenerationLicence not stated · 18 schemas
- video28 endpointsLTX 2.3 QualityImage EditingImage to VideoLoRA Training+4Licence not stated · 28 schemas
- image25 endpointsFlux 2Lightweight open FLUX.2 Dev for fast generation and indexed multi-reference editing, plus Klein, Turbo, and Flash tiers.Image EditingLoRA TrainingLicence not stated · 25 schemas
- video18 endpointsWanWan 2.2 video with cinema-grade aesthetic controls across 5B, 14B, distill, and fast tiers.Image to ImageImage to VideoSpeech+3Licence not stated · 18 schemas
- audio24 endpointsStable Audio 3Music GenerationText to AudioLicence not stated · 24 schemas
- video12 endpointsByteDance Seedance 2.0Video generation family with Fast, Mini, and regional tiers across image, reference, and text-driven endpoints.Image to VideoReference to VideoText to VideoLicence not stated · 12 schemas
- video12 endpointsKling Video V3Kling V3 4K image- and text-to-video with native single-step output, plus Pro and Standard tiers.Image to VideoText to VideoVideo EditingLicence not stated · 12 schemas
- image12 endpointsZ Image6B-parameter Turbo text-to-image with 8-step inference plus ControlNet, i2i, inpaint, and LoRA tiers.Image EditingImage GenerationImage to Image+1Licence not stated · 12 schemas
- video12 endpointsBlack Forest Labs Flux 3Image to VideoText to VideoVideo EditingLicence not stated · 12 schemas
- audio11 endpointsElevenLabsEleven v3 speech with audio-tag emotion control across 70+ languages plus 10 more endpoints.Music GenerationSpeechText to AudioLicence not stated · 11 schemas
- video13 endpointsVeo 3.1Veo 3.1 flagship video with true 4K, native audio, dialogue clarity, and extend-video narratives.Image to VideoReference to VideoVideo EditingLicence not stated · 13 schemas
- image10 endpointsQwen Image Edit 2509 LoRA GalleryImage GenerationLicence not stated · 10 schemas
- image10 endpointsQwen Image Edit Plus LoRA GalleryImage GenerationLicence not stated · 10 schemas
- image9 endpointsImage PreprocessorsImage GenerationLicence not stated · 9 schemas
- audio9 endpointsKokoro82M-parameter Kokoro TTS with 19 voices across 9 language endpoints.Text to AudioLicence not stated · 9 schemas
- video8 endpointsLongcat Video480p and 720p image- and text-to-video family delivering 720p30 clips with prompt-guided motion.Image to VideoText to VideoLicence not stated · 8 schemas
- video8 endpointsSam 3Eight-endpoint SAM 3 family for detection, segmentation, tracking, embeddings, and 3D reconstruction.3D GenerationImage GenerationVideo EditingLicence not stated · 8 schemas
- video8 endpointsWan V2.7Image EditingImage to VideoReference to Video+3Licence not stated · 8 schemas
- video8 endpointsLTX 2.3LTX-2.3 video across audio-sync, extend, retake, reframe, and fast image and text endpoints to 20 seconds.Image to VideoText to VideoVideo EditingLicence not stated · 8 schemas
- video7 endpointsBria VideoImage EditingVideo EditingLicence not stated · 7 schemas
- image7 endpointsTopaz UpscaleImage EditingLicence not stated · 7 schemas
- video7 endpointsWan V2.6Image to ImageImage to VideoReference to Video+2Licence not stated · 7 schemas
- video10 endpointsMiniMax H3H3 (Hailuo-03) LoRA trainers for keyframe, image, reference, and text video-audio modes.Image to VideoReference to VideoText to VideoLicence not stated · 10 schemas
- video10 endpointsWorkflow UtilitiesImage GenerationVideo EditingLicence not stated · 10 schemas
- video6 endpointsByteDance Seedance 2.5Next-generation video model producing up to 30 seconds of cinematic video with native audio from image, reference, or text.Image to VideoReference to VideoText to VideoLicence not stated · 6 schemas
- image6 endpointsHunyuan 3D3D GenerationImage GenerationLicence not stated · 6 schemas
- image6 endpointsHunyuan3dOctree image-to-3D reconstruction producing production GLB meshes for games, AR/VR, and artists.3D GenerationLicence not stated · 6 schemas
- video6 endpointsLightricks LTX 2.5Image to VideoText to VideoVideo EditingLicence not stated · 6 schemas
- video6 endpointsSonilo V1.1Music GenerationVideo EditingVideo to VideoLicence not stated · 6 schemas
- video5 endpointsBernini RImage GenerationReference to VideoText to Video+1Licence not stated · 5 schemas
- audio5 endpointsQwen 3 TTSText to AudioLicence not stated · 5 schemas
- video5 endpointsxAI Grok Imagine VideoImage to VideoReference to VideoText to Video+1Licence not stated · 5 schemas
- image9 endpointsIdeogram V4V4 LoRA trainer teaching subjects, characters, and styles from captioned zip archives.Image to ImageLoRA TrainingLicence not stated · 9 schemas
- video6 endpointsMiniMax H3 MaxH3-Max family with camera controls, director, image, lip-sync, reference, and text video modes.Image to VideoReference to VideoText to VideoLicence not stated · 5 schemas
- video6 endpointsPixverse V3.5V3.5 image-to-video with motion modes and style presets, plus two-image transitions and fast tiers.Image to VideoText to VideoLicence not stated · 6 schemas
- video6 endpointsPixverse V4.5Image to VideoText to VideoLicence not stated · 6 schemas
- image6 endpointsRecraft V4.1Text to ImageLicence not stated · 6 schemas
- image5 endpointsByteDance SeedreamImage editing and text-to-image family with Lite and Pro tiers, supporting reference-guided multi-image generation.Image EditingText to ImageLicence not stated · 5 schemas
- video5 endpointsPixverse V4Image to VideoText to VideoLicence not stated · 5 schemas
- video4 endpointsAlibaba Happy HorseVideo generation family covering text-to-video, image-to-video, reference-to-video, and video editing with native audio.Image to VideoReference to VideoText to Video+1Licence not stated · 4 schemas
- video4 endpointsByteDance V1Seedance 1.0 Pro text- and image-to-video endpoints in standard and Fast tiers for production workflows.Image to VideoText to VideoLicence not stated · 4 schemas
- video4 endpointsCosmos Predict 2.5Image to VideoText to VideoVideo to VideoLicence not stated · 4 schemas
Catalog truth
Cataloged is not executable.
A catalog listing documents a model or endpoint. It does not by itself mean that model is currently executable in Ethen Studio. Studio resolves which endpoints a project can run, per project, after sign-in.
- Eligible
- 912
- Under review
- 586
- Excluded
- 2
FAQ
Does a catalog listing mean the model runs in Ethen Studio?
No. A listing documents that Ethen's media catalog records the model or endpoint — its tasks, schema state, and provenance. Whether a project can run it is resolved inside Studio, per project, after sign-in.
What is the difference between a family and an endpoint?
A family is one model release, such as a text-to-video model. An endpoint is one callable shape of that family: text-to-video, image-to-video, and editing variants of the same release are separate endpoints. Families keep identity stable while endpoints track every callable variant.
Where does the catalog data come from?
Ethen Studio's canonical media catalog, delivered today through fal.ai. The public library is a read-only projection of that authority: same families, same endpoints, same counts — no separate list.
Do I need to sign in to browse the library?
No. The Media Model Library is public. Sign-in matters only inside Ethen Studio, where availability is resolved per project.
Create with the catalog behind you.
The library documents what exists. Studio is where briefs become images, video, and audio.