Wan 3.0 AI Video Generator

BETA
Model
Name
Mode
Duration
Prompt (Desired Effect)
0/5000
Generate AudioOn
Ultra users onlyLearn More & Upgrade β€Ί
Wan 3.0 Image to Video Guide

Basic Usage

1

Choose Task Type

Wan 3.0 supports First Frame, First & Last Frame, and Reference to Video modes. Use a single image, start/end frames, or multimodal references to guide the generated video.
2

Upload Media & Write Prompt

Upload the matching media for the selected mode, including images, videos, audio, or reference documents/webpages, and describe the motion, camera movement, and atmosphere you want.
3

Configure and Generate

Select video duration, resolution and other parameters, then click "Generate Video" to start creating

Task Types

First FrameUpload an image as the first frame and AI generates subsequent frames based on your prompt. Supports audio upload for videos with sound
First & Last FrameUpload first and last frame images separately. AI automatically fills in the transition animation. Use the swap button to quickly switch frames
Reference to VideoUpload multiple reference images, videos, or audio, or provide document/webpage references. Wan 3.0 uses them together to guide the generated video.
PromptDescribe video content and dynamic effects in detail. Include scene descriptions, character actions, camera movements, etc.
Negative PromptDescribe what you don't want to appear, like "blurry, low quality, deformed", to improve generation quality
Video DurationSupports 3 to 30 second videos. In Reference to Video mode, available duration is adjusted based on the uploaded reference video length.
ResolutionSupports 480P, 720P, 1080P. Higher resolution means clearer quality but requires more credits
Prompt ExpansionWhen enabled, AI will automatically expand and enrich your prompt to generate more creative video content

Tips

Choose High-Quality MediaHigh-definition, well-composed images or videos produce better results. Avoid blurry or low-resolution media
Describe Specific ActionsIncluding specific action descriptions in prompts, like "walking slowly", "nodding gently", yields more precise effects
Use First & Last Frame ModeFirst & Last Frame mode is ideal for creating expression changes, pose transitions, and scene shifts where precise control of start and end frames is needed
Plan Reference DurationFor Reference to Video, keep total reference video duration within 15 seconds. The output duration is adjusted so the combined input and output stay within the 30 second limit.

Frequently Asked Questions

  • What is Wan 3.0 and what can it generate?

    Wan 3.0 is the newest model in Alibaba's Wan series. It generates 3 to 30 second clips up to 1080P from a prompt alone, from a first frame, from first and last frames, or from a mix of references.

  • What can I use as a reference in Wan 3.0?

    Reference-to-video accepts up to 10 assets and mixes types β€” images for identity and styling, video for motion and camera language, audio for voice and sound, plus document and webpage references for the content itself.

  • Should I use Wan 3.0 or Wan 2.7?

    Wan 3.0 goes longer, up to 30 seconds, and takes the widest range of reference material. Wan 2.7 is the one to pick when you need to work on an existing clip, since it adds video extend and instruction-based video editing.

  • How do I keep a character consistent across a long clip?

    Anchor the model instead of relying on one vague prompt: supply reference images or start and end frames, say which reference controls identity and which controls style, and list what must stay unchanged β€” faces, props, brand text.

  • Do I need to sign up, and is it free to try?

    You can start for free. New accounts get bonus credits on signup, there is no credit card required, and the free plan has no daily generation limit. You can also claim extra credits every day by checking in. Everything runs in the browser on MakeFun AI β€” no GPU, no install, and no API key.

  • Can I use the videos I generate for commercial projects?

    Yes. Videos generated on a paid MakeFun AI plan can be used commercially β€” ads, social media monetization, client deliverables and product marketing. You keep ownership of the output, with no watermark, no attribution requirement and no per-clip royalties.

  • Where do my videos go after generation?

    Every finished job appears in the My Results tab beside the generator, where you can preview, download, share or delete it. The list keeps the last 3 days of generations, so download anything you want to keep before it rolls off.