wan-2-2/animate/video-to-video
Transforms input clips into synced animated characters with precise motion replication.
FLUX 3 Video is Black Forest Labs' text-to-video model that turns a written brief into a short cinematic clip, with optional synchronized native audio in the same pass. On RunComfy you can iterate in the model UI and reuse the same settings over HTTP API.
Output format: Video / up to 20 seconds / 720p or 1080p / optional native audio
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | string | — | — | Text describing the video you want to generate. |
| 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 | Clip length 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 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 |
1) Open FLUX 3 Video on RunComfy and write a clear prompt for subject, camera, motion, and sound.
2) Set Aspect Ratio to match delivery (for example 16:9 landscape or 9:16 vertical), or leave auto.
3) Choose Resolution: start at 720p while iterating, then switch to 1080p for final delivery.
4) Pick Duration as a fixed length (5–20 s) or leave auto so the model decides.
5) Keep Generate Audio on when you want speech, SFX, or ambience; turn it off for silent video.
6) Optionally adjust Safety Tolerance if the scene needs a stricter or looser filter.
7) Generate, review the clip, then refine the prompt or duration before scaling up.
8) For API use on RunComfy, send the same parameters; results appear in your job history.
In short, FLUX 3 Video on RunComfy turns prompts into cinematic clips with optional native audio at 720p or 1080p, ready for browser iteration and API production.
Transforms input clips into synced animated characters with precise motion replication.
Edit a source video from a text instruction while keeping scene coherence.
Create rapid high-quality video drafts with precise style and speed
FLUX 3 Draft: Fast, low-cost text-to-video previews at 720p
HappyHorse 1.0 I2V on Alibaba animates a still image into native 1080p video with physics-accurate motion and identity-stable subjects.
Turn text into detailed cinematic scenes with Dreamina 3.0 precision.
FLUX 3 Video turns a text prompt into a short cinematic clip with optional synchronized native audio. It targets ad creative, film previsualization, and branded storytelling where prompt-driven motion and sound matter.
You can set duration to auto or lock a fixed length from 5 to 20 seconds. Auto lets the model choose; fixed lengths give you predictable pacing for dialogue and dramatic beats.
Yes. Generate Audio is on by default, so the model can output synchronized speech, SFX, and ambience with the picture. Turn it off when you need silent video.
Resolution options 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.
Only the prompt is required. Optional fields are aspect_ratio, resolution, duration, generate_audio, and safety_tolerance (0–4, default 2).
Safety tolerance controls how strict content filtering is. 0 is the strictest setting and 4 is the most permissive; the default is 2.
Black Forest Labs has announced FLUX 3 editions including hosted video, image, action prediction, and a planned FLUX 3 Dev open-weight backbone. Once that backbone lands, community LoRA workflows for recurring characters and brand looks are the natural next step.
Prototype in the RunComfy model UI, then call the same template through the RunComfy API using identical Input fields (prompt, aspect_ratio, resolution, duration, generate_audio, safety_tolerance). Validate prompts in the UI first, then use your account API key and credits for automated jobs.
Billing is based on generated video duration and resolution: $0.17 per second at 720p, and $0.29 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.
