kling-video-o3/standard/text-to-video
Generate cinematic 3-15s videos from text with optional sound.
Upload a short source clip, describe what should happen next, and get a continuation that picks up from the final frames. On RunComfy you set the Input in the model UI, then reuse the same fields over HTTP API.
Output format: Video / source clip under 15 s / extension auto or 5–20 s / 720p or 1080p / optional native audio
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Text describing how the video continues from the source clip's final frames. |
| video_url* | Yes (*) | string (video_uri) | — | MP4, under 50 MB and under 15 seconds | URL of the input video to extend. |
| 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 | string | auto | auto, 5–20 | Length of the generated segment in seconds; auto lets the model choose. |
| 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 Extend Video is based on the length of the generated segment and the selected resolution.
| Resolution | Rate |
|---|---|
| 720p | $0.45 per second |
| 1080p | $0.59 per second |
Estimated cost examples (720p)
| Duration | Approx. cost |
|---|---|
| 5 s | ~$2.25 |
| 10 s | ~$4.50 |
| 20 s | ~$9.00 |
Estimated cost examples (1080p)
| Duration | Approx. cost |
|---|---|
| 5 s | ~$2.95 |
| 10 s | ~$5.90 |
| 20 s | ~$11.80 |
Generate cinematic 3-15s videos from text with optional sound.
Transforms static characters into smooth motion clips for flexible creative workflows
Seedance 2.5: Cinematic AI video with stronger consistency and longer clips
Generate premium videos with synced audio from text using OpenAI Sora 2 Pro.
Streamline video refinements with seamless scene continuity for creators.
Multimodal AI video model with native audio for text, image, and reference inputs.
FLUX 3 Extend Video continues an existing clip past its final frames using a written prompt. It helps editors, marketers, and previz teams lengthen a locked opening take without rebuilding the whole shot from scratch.
FLUX 3 Extend Video requires a prompt and a video_url. The source video should be MP4, under 50 MB, and under 15 seconds. Optional fields include aspect_ratio, resolution, duration, generate_audio, and safety_tolerance.
You can set duration to auto or lock any whole-second length from 5 to 20 for the generated segment. Auto lets the model choose; fixed lengths give predictable pacing when you chain multiple FLUX 3 Extend Video passes.
Resolution options for FLUX 3 Extend Video are 720p (default) and 1080p. Aspect ratio defaults to auto, or you can lock 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16 for known delivery formats.
Yes. Generate Audio is on by default in FLUX 3 Extend Video, so the model can output synchronized speech, SFX, and ambience with the new footage. Turn it off when you need silent video.
Text-to-video invents a full clip from a prompt alone. FLUX 3 Extend Video is video-to-video: it conditions on your source clip’s trailing frames and generates the next stretch so motion and scene can stay aligned with what you already shot.
Prototype FLUX 3 Extend Video in the RunComfy model UI, then call the same template through the RunComfy API with identical Input fields (prompt, video_url, aspect_ratio, resolution, duration, generate_audio, safety_tolerance). Validate prompts and joins in the UI first, then use your account API key and credits for automated jobs.
Billing for FLUX 3 Extend Video is based on generated video duration and resolution: $0.45 per second at 720p, and $0.59 per second at 1080p. See the pricing shown on this page for the latest rates.
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.
