Beta
Docs
Providers & Models

Video Providers

All video generation models currently available in Hylope, organized by provider.

Picking a video model starts with what you're feeding it: a blank prompt, a single start frame, two keyframes to interpolate between, reference clips, or existing footage to edit. The tables below cover every provider's models, resolutions, and durations for Video Generation mode — or jump straight to the sub-mode map at the bottom to find every model that supports the workflow you need.

Resolution and duration depend on the model, not your plan

Every model is available on every paid plan, billed per generation from your credit balance. What resolutions and durations you get come from the model you pick, not your subscription tier.

Model coverage matches the in-app Video Generation picker. For pricing, see the Pricing page. Plan differences: Plans & Billing.


Google Google

Veo

Google video generation with up to 4K on supported models.

ModelSub-modesNotes
Veo 3.1 LiteText to Video, Start Frame, InterpolationMost affordable Veo; default
Veo 3.1 Fast+ ReferencesQuick previews
Veo 3.1+ ReferencesFull quality

Resolutions: 720p, 1080p, 4K · Duration: 4 / 6 / 8s (1080p and 4K lock to 8s)

Gemini

ModelSub-modesNotes
Omni Flash (preview)Text to Video, Start Frame, References, EditFast 720p only; 3–10s; up to 4 image references

Alibaba Alibaba

HappyHorse

ModelSub-mode
HappyHorse 1.1 T2VText to Video
HappyHorse 1.1 I2VStart Frame (default)
HappyHorse 1.1 R2VReferences (image refs)
HappyHorse 1.0 Video EditEdit

HappyHorse 1.0 T2V / I2V / R2V are superseded in the picker but remain for restoring older generations. 1.0 Video Edit stays available.

Resolutions: 720p / 1080p · Duration: 3–15s · seeds, optional watermark

Wan

ModelSub-modes
Wan 2.7 T2VText to Video
Wan 2.7 I2VStart Frame, Interpolation, Continuation
Wan 2.7 R2VReferences (image or video refs)
Wan 2.7 Video EditEdit
Wan 2.6 Flash / Wan 2.6Start Frame (legacy)
Wan 2.2 KF FlashInterpolation (legacy)
Wan 2.6 R2V Flash / R2VReferences (legacy)

Resolutions: 480p–1080p · optional audio · negative prompts · seeds


KlingAI KlingAI

Kling

ModelSub-modesNotes
Kling 3.0 TurboText to Video, Start FrameFast; 720p / 1080p
Kling 3.0+ Interpolation, Motion ControlCore multi-shot + motion ref
Kling 3.0 OmniText to Video, Start Frame, Interpolation, ReferencesMixed-media refs; 4K on many paths
Kling AvatarAvatarTalking avatar from start frame + audio

Duration: typically 3–15s · motion control uses a motion reference input


BytePlus BytePlus / ByteDance

Seedance

ModelNotes
Seedance 2.0Multimodal generation; 480p–1080p; up to 15s; image + video refs
Seedance 2.0 FastFaster; 480p / 720p
Seedance 1.5 ProPrevious gen with audio output

OmniHuman

ModelNotes
OmniHuman 1.5Avatar sub-mode: image + required audio → talking portrait; 720p / 1080p

LTX LTX

ModelNotes
LTX 2.3 Fast1080p / 1440p / 4K; durations up to 20s
LTX 2.3 ProHigher fidelity; max 10s; audio-driven & interpolation

Sub-modes: Text to Video, Start Frame, Interpolation.


xAI xAI (Grok)

ModelSub-modesNotes
Imagine Video 1.0Text to Video, Start Frame, References, Edit, ExtendFull suite
Imagine Video 1.5Start Frame onlyImage-to-video

Resolutions: 480p / 720p · Duration: 1–15s


Luma

ModelSub-modesNotes
Ray 3.2Text to Video, Start Frame, Interpolation, Edit, ReformatHDR, seamless loop; 540p–1080p; 5 or 10s

Sub-mode map (who supports what)

The first six rows are Video Generation sub-modes; Edit, Extend, and Reformat belong to the separate Video Edit mode.

Sub-modeTypical providers
Text to VideoVeo, Gemini, Wan, HappyHorse, Kling, Seedance, LTX, Grok, Luma
Start FrameMost providers
InterpolationVeo, Wan, Kling, LTX, Luma
ReferencesVeo Fast/Full, Gemini, Wan, HappyHorse, Kling Omni, Seedance 2.0, Grok 1.0
Motion ControlKling 3.0
AvatarKling Avatar, OmniHuman
EditGemini Omni Flash, Wan 2.7, HappyHorse 1.0 Edit, Seedance 2.0, Grok 1.0, Luma
ExtendWan 2.7, Seedance 2.0, Grok 1.0
ReformatLuma Ray 3.2

On this page