Video Generation
The Video Generation node generates a video from a text prompt, a start frame image, or reference footage, depending on the model you pick.
Inputs and outputs
Most models include Start Frame (the opening frame) and Prompt. There are exceptions: Kling Motion uses a character image and a motion video instead (see below), and Sora 2 Pro takes no frames at all. Depending on the model, you may also see:
- End Frame: the closing frame, for models that support it
- Image Reference: images showing the look you want the model to follow
- Elements: your Influencer's images, so the same character shows up in the clip
- Reference Video: a clip the model takes its cues from, for models that support it
Image Reference and Elements both feed the model reference images. They are separate inputs because they do different jobs: one sets the look, the other sets who is in the shot.
Plus a generic Flow input.
Output: a single Video handle.
Writing a prompt
Type your prompt into the box at the bottom of the card ("Describe the video scene..."). If Prompt is connected from elsewhere, this box is disabled and shows "Prompt connected from input" instead.
The generated video plays in the preview area at the top with standard playback controls. Click Download in the settings bar to save it.
Choosing a model
Click the model picker to search and choose a model. The default model is PixVerse V6, with a default duration of 5 seconds, aspect ratio 9:16, and sound generation off by default.
Which provider serves the models comes from Settings, and applies to every node.
If you connect Image Reference, Elements, or Reference Video, the model picker filters itself down to models that can use that input.
Settings on the card
Shown only when the selected model supports them: Model picker, Aspect ratio chip, Duration chip (for example "5s" or "8s"), Quality chip, and a Sound on/off toggle.
Quality and aspect ratio work together. Pick the quality first, because it decides which shapes are available: a model may offer an ultra-wide 21:9 at 720p but not at 4K. The two choices resolve to an exact frame size behind the scenes, so you never have to think in pixels.
Models available
fal.ai's curated list includes model families from PixVerse, Kling, ByteDance (Seedance), Google (Veo, Gemini Omni Video), xAI (Grok Imagine Video), Wan, MiniMax (Hailuo), Lightricks (LTX), and Alibaba. OpenRouter and Kie AI offer many of the same families, plus some extras. Each model supports its own mix of text-to-video, image-to-video, or reference-to-video, with its own durations, quality tiers, and aspect ratios; check the model picker for what each one offers.
On OpenRouter you get Kling v3.0 Standard and Pro, Kling Video O1, Veo 3.1 in three tiers, Sora 2 Pro, Seedance 2.0 and 2.0 Fast and 1.5 Pro, Wan 2.7 and 2.6, both Grok Imagine Video models, Hailuo 2.3, and HappyHorse 1.1. Clip lengths run from 1 second to 20 depending on the model, and quality goes up to 4K on Seedance 2.0 and Veo 3.1. Every OpenRouter model accepts reference images. Sora is the one model that takes no start or end frame, so guide it with a prompt and reference images instead.
Kling Motion models work a bit differently: you provide one character image and one motion video, and the model transfers the motion video's movement onto your character. There's no duration or aspect ratio to set, the length follows the motion video.
Running the node
Select the node to reveal its Run button. A standalone node with no inputs runs itself; run it again to also run everything downstream. If its inputs already have results, running it runs everything downstream too. If inputs aren't ready yet, you'll be asked whether to run the whole workflow, or run everything up to and including this node.
Click the Inputs / Outputs button at any time to see exactly what data went in and came out.