Wan3.0: Text to Video
Generate videos up to 30 seconds directly from text prompts using Wan3.0-Video, producing a single video output with lifelike visuals and synchronized sound. This workflow transforms written descriptions into immersive, production-ready footage with strong character consistency and cinematic quality. Ideal for cinematic storytelling, character-driven animations, and quick multimedia content creation.
简介
This ComfyUI workflow turns plain text into a single, production-ready video clip using the Wan3.0-Video model. At the core is the Wan3ReferenceToVideoApi node, which sends your prompt (and optionally a reference image) to the Wan3.0 text-to-video service and returns a finished clip with synchronized audio. The SaveVideo node then writes the returned clip to disk as a standard video file, giving you a straightforward, single-output pipeline from idea to result.
你需要提供
- 正在读取工作流
在 ComfyUI 中运行。 此工作流无法在本页面运行。你可以在 Comfy Cloud 中打开（已预先加载所需内容），或下载后在自己的 ComfyUI 中使用。
在 Cloud 中试用常见问答
Yes. The Wan3ReferenceToVideoApi node connects to the Wan3.0-Video service and typically requires an API key or credentials. Enter these in the node settings per your ComfyUI integration.
Up to 30 seconds. Set the duration in Wan3ReferenceToVideoApi within that limit. Longer requests may fail or be truncated by the service.
Provide a clear reference image in Wan3ReferenceToVideoApi and keep your prompt and seed (if available) consistent across runs. Describe defining traits (clothing, colors, hairstyle) explicitly in the prompt.
Yes. The Wan3.0 service returns a single video file with synchronized sound. SaveVideo writes the received video to disk, preserving the embedded audio. If you don’t hear sound, verify your media player and the saved container support audio.