Wan 3.0 Prime text-to-video

Wan 3.0 Prime is a text-to-video model from Alibaba’s Wan family. Describe a scene in natural language and it generates a video with coherent motion and lighting.

The model generates video at 480p, 720p, or 1080p, with durations from 2 to 30 seconds. Let the model pick the best aspect ratio for your prompt with the adaptive setting, or choose your own.

Inputs

• prompt — Text description of the video to generate (required)
• negative_prompt — Describes content that should not appear in the video
• resolution — 480p, 720p, or 1080p (default: 1080p)
• aspect_ratio — adaptive, 16:9, 9:16, 1:1, 4:3, or 3:4 (default: adaptive)
• duration — Length in seconds, 2–30 (default: 5)
• enable_prompt_expansion — Automatically expand short prompts for better results. Improves quality but adds latency (default: true)
• seed — Random seed for reproducible results

Tips

• Be descriptive. Include details about the scene, lighting, camera movement, and action. “A golden retriever running through autumn leaves in a park, camera tracking from the side, warm afternoon light” works much better than “a dog in a park.”
• Use negative prompts to reduce common artifacts — try “blurry, distorted, low quality, static.”
• Enable prompt expansion for short prompts. It fills in visual details that improve generation quality.
• Pick the right aspect ratio for your use case — 9:16 for vertical/mobile content, 16:9 for widescreen, 1:1 for social. Or use adaptive to let the model decide.

Limitations

• Complex multi-character scenes with specific interactions can be inconsistent.
• Text rendering within generated videos is unreliable.
• Longer durations may show motion degradation or scene drift.
• Precise spatial relationships (“object A is to the left of object B”) are not always followed exactly.

Links

• GitHub
• Apache 2.0 License