kling/lipsync/text-to-video
Create lifelike speech-synced visuals from scripts or clips with Kling Lipsync for precise facial animation and realistic results.
Pin up to ten stills to specific frame indices, add a written brief for the motion between them, and get a short clip with optional synchronized native audio. On RunComfy you can set the anchors in the model UI, then reuse the same Input over HTTP API.
Output format: Video / up to 10 keyframes / 5–20 seconds / 720p or 1080p / optional native audio
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Text describing the video and the motion between keyframes. |
| keyframes* | Yes (*) | array | — | 1–10 items | Keyframe images pinned to frame positions; each needs image_url and unique frame_index (0-based, at most duration × 24). |
| aspect_ratio | No | string | auto | auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 | Output frame shape; auto lets the model choose. |
| resolution | No | string | 720p | 720p, 1080p | Output resolution. |
| duration | No | integer | 5 | 5–20 | Clip length in seconds; required in practice to validate keyframe positions. |
| generate_audio | No | boolean | true | true, false | Whether to generate synchronized audio. |
| safety_tolerance | No | integer | 2 | 0–4 | 0 is strictest; 4 is most permissive. |
Billing for FLUX 3 Keyframes to Video is based on the length of the generated clip and the selected resolution.
| Resolution | Rate |
|---|---|
| 720p | $0.17 per second |
| 1080p | $0.29 per second |
Estimated cost examples (720p)
| Duration | Approx. cost |
|---|---|
| 5 s | ~$0.85 |
| 10 s | ~$1.70 |
| 20 s | ~$3.40 |
Estimated cost examples (1080p)
| Duration | Approx. cost |
|---|---|
| 5 s | ~$1.45 |
| 10 s | ~$2.90 |
| 20 s | ~$5.80 |
Create lifelike speech-synced visuals from scripts or clips with Kling Lipsync for precise facial animation and realistic results.
HappyHorse 1.0 with native 1080p output, cinematic motion, and multi-shot consistency.
Precise prompts, lifelike motion, vivid video quality.
Generate cinematic 3-15s videos from text with optional sound.
Image-to-video 3-15s clips at $0.084 per second.
Animate static portraits with smooth, identity-true motion using Steady Dancer's video-driven generation.
FLUX 3 Keyframes to Video is built for shots where you already know several visual beats. You pin stills to frame indices, describe the motion in a prompt, and the model fills the path between those anchors as one continuous clip with optional native audio.
You can supply up to 10 keyframes. Each item needs an image URL and a unique frame_index on the 24 fps timeline, and that index must stay within duration × 24 for the length you choose.
First-and-last-frame modes lock only the opening and closing stills. FLUX 3 Keyframes to Video lets you place additional mid-clip anchors, so turns, product holds, and pose changes can land on exact frames instead of drifting between two endpoints.
Clips are whole seconds from 5 to 20, at 720p or 1080p, with aspect ratios from ultrawide 21:9 through vertical 9:16 plus auto. Audio generation can be turned on or off, and safety tolerance ranges from 0 (strictest) to 4.
Yes in practice. Duration is how the model validates that every frame_index fits the clip, so pick a length from 5 to 20 seconds before you place mid-timeline keyframes.
Storyboard artists, product marketers, and previz teams use FLUX 3 Keyframes to Video when a shot must hit several planned compositions in order. It is less ideal when you only have one still and want free-form animation from a single image.
Yes. Prototype the prompt, keyframes, duration, and resolution in the RunComfy Web UI, then call the same model over the HTTP API with matching parameters for automation. Generations consume usd / credits on both paths.
Billing follows the generated clip length and resolution: $0.17 per second at 720p and $0.29 per second at 1080p. Check the Generation section on this page for the live credit conversion when you submit a run.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
