Computational Model Studio · Model release
Kling Video 3.0
Generate and edit multi-shot video from prompts and visual references, with native audio.
Developer: Kuaishou · Last verified:
What it is designed to do
Generate and edit multi-shot video from prompts and visual references, with native audio.
- Primary contribution
- generation transformation
- Input
- text, image, video
- Output
- video, audio (generated video with native audio)
Documented uses: Generate and edit multi-shot video from prompts and visual references, with native audio.
Access and deployment
- Kling Video 3.0 web experience — available. Use the publisher’s web experience with an eligible account and select the documented model. Offering documentation Complete publisher web service terms were not reviewed for this offering.
- provider hosted: Select Video 3.0 in the publisher’s documented web experience. Limits: A public API model ID or local weight artifact is not inferred from this web selector..
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- active
Inclusion rationale: Kling Video 3.0 provides a recognizable web-accessible video-and-audio output model from Kuaishou.
Limitations
- The publisher’s described output is recorded as the exact media form shown; surrounding editing tools or orchestration are not attributed to this model.
- The documented web model selector does not establish an exact public API model ID or downloadable weights.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- Supports functionGenerate video
- OfferingKling Video 3.0 web experience