wan-2-2/text-to-video
Generate high quality videos from text prompts with Wan 2.2 Plus.
Black Forest Labs' FLUX 3 Image to Video starts from a still image and a written brief, then builds a short clip with optional synchronized native audio at 720p or 1080p, for up to 20 seconds per generation.
Trading manual timeline animation and separate sound design for prompt-guided motion from a locked start frame, FLUX 3 Image to Video helps marketers, product teams, and previz artists turn stills into usable clips faster.
For developers, FLUX 3 Image to Video on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Product Still Animation | Character Opening Shots | Ad Creative From Key Art
FLUX 3 Image to Video takes a still frame plus a written brief and turns them into a short clip with optional synchronized native audio. On RunComfy you can tune motion in the model UI, then reuse the same Input over HTTP API.
Output format: Video / starts from one image / up to 20 seconds / 720p or 1080p / optional native audio
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| image_url* | Yes (*) | string | — | PNG, JPEG, WebP URL | Start frame the clip begins from. |
| prompt* | Yes (*) | string | — | — | Text describing how the video should unfold from the image. |
| 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 for FLUX 3 Image to Video is based on the length of the generated clip and the selected resolution.
| Resolution | Rate |
|---|---|
| 720p | $0.187 per second |
| 1080p | $0.319 per second |
Estimated cost examples (720p)
| Duration | Approx. cost |
|---|---|
| 5 s | ~$0.94 |
| 10 s | ~$1.87 |
| 20 s | ~$3.74 |
Estimated cost examples (1080p)
| Duration | Approx. cost |
|---|---|
| 5 s | ~$1.60 |
| 10 s | ~$3.19 |
| 20 s | ~$6.38 |
Generate high quality videos from text prompts with Wan 2.2 Plus.
Seedance 2.5 Reference to Video 4K: multi-reference 4K clips
Create lifelike speech-synced visuals from scripts or clips with Kling Lipsync for precise facial animation and realistic results.
Create 1080p clips with multi-reference and frame control.
Reference-driven 3-15s video generation at $0.084 per second.
Seedance 2.5 1080p: Animate stills into sharp, natural 1080p video
FLUX 3 Image to Video starts from a still image and a text prompt, then generates a short clip with optional synchronized native audio. It fits product animation, character openers, and ad creative when the first frame is already locked.
FLUX 3 Image to Video anchors the opening look to your uploaded still, then continues motion from that frame. Text-to-video FLUX 3 invents the entire shot from a prompt alone, without a required start image.
Yes. Generate Audio is on by default, so FLUX 3 Image to Video can output synchronized speech, SFX, and ambience with the picture. Turn it off when you need silent video.
You can set duration to auto or lock a fixed length from 5 to 20 seconds. Auto lets the model choose; fixed lengths give predictable pacing for product beats and dialogue.
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.
image_url and prompt are required. Optional fields are aspect_ratio, resolution, duration, generate_audio, and safety_tolerance (0–4, default 2). The start image should be a PNG, JPEG, or WebP URL.
Prototype in the RunComfy model UI, then call the same template through the RunComfy API using identical Input fields (image_url, prompt, aspect_ratio, resolution, duration, generate_audio, safety_tolerance). Validate prompts and start frames in the UI first, then use your account API key and credits for automated jobs.
Billing is based on generated video duration and resolution: $0.187 per second at 720p, and $0.319 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.
