Video to Video
Transform a whole video from a prompt. Restyle footage as anime or claymation, turn day into night, or edit a clip by instruction with Seedance 2.5 Edit.
The Video to Video node transforms an existing video from a text prompt. It keeps the motion of the source clip and changes what you describe: the style, the light, the season or a detail. Use it for style transfer, for variations of existing footage and, with Seedance 2.5 Edit, for edits written as instructions such as make it black and white.
When to use it
- Recorded footage should look painterly, anime, claymation or cinematic.
- A scene should change its conditions, for example from day to night or from summer to winter.
- You want several variations of the same clip.
- You want to edit a clip by instruction and bring in an outfit, an object or a place from reference images. Use Seedance 2.5 Edit.
To change only a few seconds of a clip, use Retake Video. To relight a subject or swap a background from the clip's own pixels, use Relight & Switch.
Quick start
Add the node
Press Tab on the canvas and choose Video › Continue & Restyle › Video to Video.
Connect the clip
Wire the source video into the Video input. Short clips of 5 to 10 seconds give the best results.
Choose a model and describe the change
Open the settings panel and choose a model under Provider. Describe the transformation, for example change to anime style, rather than the whole scene. You can also start from a preset in the Restyle Looks folder.
Run it
Click Run on the node. The transformed video appears on the node.
Inputs
| Input | Accepts | What it does |
|---|---|---|
| Video | Video nodes, such as Upload Video, Generate Video and Extend Video | The source clip. Required. |
| Prompt | Text nodes | The transformation. A wired prompt replaces the prompt typed in the settings panel. |
| Negative | Text nodes | What to avoid. Seedance 2.5 Edit ignores it. |
| Cinematography | Camera and look pickers, such as Style, Lighting and Color / Look | Each picker adds its choice to the prompt. |
| Image Refs | Image nodes | Seedance 2.5 Edit only. Up to 30 reference images. |
| Audio Refs | Audio nodes | Seedance 2.5 Edit only. Up to 10 reference audio clips. |
The two reference inputs are always visible. On every other model they are dimmed and report that the model does not support them, and a connection to them has no effect.
The output, Video, is the transformed clip.
Settings
| Setting | What it does |
|---|---|
| Provider | The model. The default is Wan 2.6. |
| Prompt | The transformation to apply. |
| Negative Prompt | What to avoid. Not sent with Seedance 2.5 Edit. |
| Pre & post text | Text that is always added before and after the prompt. It is hidden from people who use your workflow as an app. See Prompt pre and post text. |
Each model adds its own settings:
| Model | Extra settings |
|---|---|
| Seedance 2.5 Edit | Resolution: 480p (the default), 720p or 1080p. Generate Audio: native sound on the result, on by default. Seed: a fixed number for repeatable results. |
| Wan 2.6 | Duration: 5 seconds (the default) or 10 seconds. Resolution: 720p or 1080p (the default). |
| Wan 2.6 Flash | The same Duration and Resolution as Wan 2.6, plus Generate Audio, which changes the price, and Multi-shot composition. Both are off by default. |
| Wan 2.7 VideoEdit | Duration: Auto (the default), 5 seconds or 10 seconds. Resolution: 720p or 1080p (the default). Audio: Auto (AI-generated) or Original audio, which keeps the source sound. Expand prompt with AI: off by default. Seed. |
| Runway Aleph | Aspect Ratio: Auto, 16:9, 9:16, 4:3, 3:4, 1:1 or 21:9. Seed. |
| Luma Modify and HappyHorse Edit | No extra settings. |
Models
Video to Video offers seven models. Click a model for its settings and credit prices.
| Model | Maker | Modes | Credits | Details |
|---|---|---|---|---|
| Seedance 2.5 | Bytedance | Image to video, Text to video | from 340 | Seedance 2.5 — up to 30s in one shot, native audio, wide multimodal references. 480p/720p/1080p. |
| Wan 2.6 | Alibaba | Video to video, Text to video | from 175 | Wan 2.6 — text-to-video and video-to-video under a single id. |
| Wan Flash V2V | Alibaba | Video to video | 100 | Faster Wan V2V variant. |
| Wan 2.7 VideoEdit | Alibaba | Video to video | 320 | Guided video editing with optional reference image, audio control, and prompt expansion. |
| Runway Aleph V2V | Runway | Video to video | 350 | Runway Aleph — video-to-video conversion. |
| HappyHorse Edit | HappyHorse | Video to video | 350 | HappyHorse video-edit — video-to-video transformation, up to 60s input, 720p/1080p output. |
The node also offers Luma Modify, which is strong at style transfer and artistic changes.
Which model to choose
The model table uses the catalog names: Wan 2.6 Flash is listed as Wan Flash V2V, Runway Aleph as Runway Aleph V2V, and Seedance 2.5 Edit as Seedance 2.5.
- Wan 2.6 Flash is the cheapest and the fastest. Use it to test an idea.
- Wan 2.6 is a general-purpose model with reliable results.
- Wan 2.7 VideoEdit adds control over the sound and can expand a short prompt with AI.
- Runway Aleph gives high-quality transformations and a free choice of aspect ratio.
- Luma Modify is strong at style transfer and artistic changes.
- HappyHorse Edit accepts source clips up to 60 seconds long.
- Seedance 2.5 Edit edits the clip by instruction, keeps its length and aspect ratio, and accepts image and audio references.
Edit by instruction with Seedance 2.5 Edit
Seedance edits a video that it receives as a reference when the prompt reads as an edit instruction. The node prepares the run for you:
- The source clip becomes reference video 1. Your prompt is sent as
edit @video_1 as follows:followed by your text. If your prompt already starts with that instruction, it is not added twice. - The result keeps the source clip's length and aspect ratio. That is why this model has no Duration and no Aspect Ratio setting.
- The source clip must be 4 to 30 seconds long. Shorter or longer clips are refused.
- Negative prompts are not sent. Write what to avoid into the instruction itself.
Write the prompt as an instruction about the clip:
make it black and white, heavy film grainWire images into Image Refs and cite them by position, in the order you connected them. {image:1} is the first image, {image:2} is the second, and so on. Reference audio works the same way, with {audio:1}.
the woman wears {image:1} and stands in {image:2}Generate Video has an Edit Video preset that runs the same kind of Seedance 2.5 edit.
Presets
The Restyle Looks folder in the node's preset menu has six ready-made looks: Anime Restyle, Claymation, Cyberpunk Neon, Oil Painting, 3D Animated and Watercolor. Each preset selects Wan 2.6, a negative prompt that suppresses flicker and distortion, and a restyle instruction that keeps the original motion. The instruction is stored as pre text, so the prompt stays free for your own additions. See Presets.
Credits
- Wan 2.6, Wan 2.6 Flash, Wan 2.7 VideoEdit, Runway Aleph, Luma Modify and HappyHorse Edit are priced per model. The model table above lists the prices, and the node shows the price before you run it.
- Seedance 2.5 Edit is billed like a Seedance run with a reference video in Generate Video: the per-second rate of the chosen resolution, times the length of the source clip plus the length of the result. Because the result length is automatic, the run reserves credits for the longest possible result, 30 seconds. It then refunds the difference down to the length actually delivered, which is the length of the source clip. Your balance must cover the reservation for the run to start.
Tips
- Change the style, not the structure. Colors, textures and light change reliably. Adding or removing objects works less well. For structural changes, edit keyframes with Generate Image and animate them with Generate Video.
- Describe only the change.
change to anime styleworks better than a description of the whole scene. - Test cheap, finish sharp. Try the idea on Wan 2.6 Flash, then run the final version on Runway Aleph or Luma Modify.
- Iterate Seedance at 480p. The reservation grows with the resolution, so switch to
1080ponly for the final run. - Expand short prompts. With Wan 2.7 VideoEdit, turn on Expand prompt with AI when your prompt is very brief.
- Keep prompts consistent. When you restyle several clips of one project, use the same prompt or the same preset for all of them.
Frequently asked questions
Related
Generate Video
Retake Video
Relight & Switch
Presets
Seedance 2.5
Last updated on
Retake Video
Regenerate a time window of an existing video with LTX 2.3 Pro. Replace only the sound, only the picture or both, and keep everything outside the window.
Relight & Switch
Relight a subject, swap or restyle a background, or composite new elements into a video, driven by the clip's own pixels, a mask and a reference image.