curl-X POST 'https://pollo.ai/api/platform/v1/generation/alibaba/wan-v3-0/video'\-H'Content-Type: application/json'\-H'x-api-key: YOUR_API_KEY'\-d'{ "input": { "prompt": "A cinematic shot of a golden retriever running through a field of sunflowers at sunset, warm rim light, shallow depth of field", "duration": 5, "resolution": "480p", "aspectRatio": "adaptive", "generateAudio": true }}'
Optionally include webhookUrl to receive a callback when the task succeeds or fails.
Optional request field
{"input":{"prompt":"A cinematic shot of a golden retriever running through a field of sunflowers at sunset, warm rim light, shallow depth of field","duration":5,"resolution":"480p","aspectRatio":"adaptive","generateAudio":true},"webhookUrl":"https://example.com/webhooks/pollo"}
Schema
Input fields for the selected endpoint and mode.
Field
Type
Required
Description
prompt
string
Yes
Text prompt describing the content to generate.
duration
integer
No
The duration of the generated video, in seconds.
resolution
string
No
Output resolution of the generated media (e.g. 720p, 1080p, 2K, 4K). Values are case-insensitive.
aspectRatio
string
No
Output aspect ratio, as width:height (e.g. 16:9).
generateAudio
boolean
No
Generate natural-sounding, fitting audio for the output video.
Carry a story beyond its opening shot with Wan 3.0. Alibaba’s video model combines reference guidance and generated sound to develop connected visual sequences.
Use Wan 3.0 on Pollo API to connect story briefs and existing creative assets with video generation inside your application, content pipeline, or production tool.
Key Features of Wan 3.0 API
Multimodal Reference Guidance
Images, video, and audio can contribute different creative cues. Use references to establish who appears, how the scene moves, and what it sounds like.
Extended Scene Development
Longer generation gives an action room to unfold. A scene can establish its setting, introduce a change, and hold on the resulting reaction.
Native Sound Generation
Dialogue, music, and environmental effects can accompany generated footage, helping spoken moments and visible actions feel like parts of the same scene rather than separate assets.
Video Revision and Continuation
The model family supports editing and extension, making existing footage a starting point for changing a scene or exploring what happens after its current ending.
Use Cases of Wan 3.0 API
Recurring Character Stories: Pair a character reference with a new setting and a short sequence of actions for the next installment.
Location-Based Narratives: Use a location image to anchor a scene that develops from an establishing view into a character interaction.
Audio-Led Scene Concepts: Explore footage built around a supplied sound reference, with the relationship between sound and action specified in the brief.
Alternative Scene Endings: Develop different reactions to the same event while keeping the preceding story context consistent.
Craft Process Stories: Show a maker inspecting a material, working on it, and revealing a result within a connected narrative.
Reference-Based Previsualization: Turn approved visual references into motion studies before committing resources to a live shoot.
How to Use Wan 3.0 API
Get an API Key: Create a Pollo API account and generate your API key from the developer dashboard.
Choose the Model: Send requests to the Wan 3.0 endpoint at /generation/alibaba/wan-v3-0/video
Add Your Inputs: Provide your prompt and supported media. Set duration, resolution, and generateAudio as needed; follow the selected mode’s current schema.
Generate and Retrieve: Submit the request, retain the returned taskId, and check task status to retrieve the completed video.
Prompting Best Practices for Wan 3.0 API
Write the scene as a small story with a visible change. Assign each reference a clear purpose, then explain the actions connecting the opening and ending.
A Simple Prompt Formula
Reference roles + setting + subject + opening action + turning point + ending reaction + camera direction + sound
What You Should Notice
Reference Roles: Explain whether each supplied asset establishes a character, setting, movement, or sound; avoid asking one asset to fulfill conflicting roles.
Story Progression: Replace a list of unrelated events with one cause-and-effect sequence that viewers can follow.
Character Anchors: Repeat the few details that must remain recognizable, such as a red scarf or a distinctive shoulder bag.
Sound Priorities: Identify the important audible event and leave quieter background sound subordinate to it.
Revision Scope: When editing, distinguish the requested change from the visual elements that should remain fixed.
Example Prompts
The Missed Delivery
“Use the supplied courier image as the character reference. A courier reaches a closed hilltop library, finds a handwritten note, then notices a light upstairs. Follow from behind, cut to the note, and finish on the lit window. Wind rustles the paper; no music.”
A Potter’s Small Discovery
“Inside a sunlit ceramics workshop, a potter lifts a bowl from a shelf and discovers a tiny leaf impression underneath. Begin with the room, move closer as she turns the bowl, then hold on her smile. Soft shelf creaks and distant street noise accompany the scene.”
An Unexpected Passenger
“Use the supplied boat image to establish the setting. A ferryman unties a rope, hears a soft bleat, and discovers a goat sitting among the baskets. Show the rope, his startled turn, and the passenger reveal. Maintain overcast morning light, with water lapping and one bleat.”
Wan 3.0 vs MiniMax H3 Max vs Wan 3.0 Prime
Selection Factor
Wan 3.0
MiniMax H3 Max
Wan 3.0 Prime
Generation inputs on Pollo
Text, image, and reference workflows
Text and image workflows
Text, image, and reference workflows
Audio
Native sound generation
Synchronized sound
Synchronized sound
Page emphasis
Longer sequences and multimodal references
Short scenes and camera direction
Multi-shot narratives and reference continuity
Suggested evaluation
Story progression and reference use
Action timing and shot execution
Character continuity across cuts
Why Choose Wan 3.0 API?
Choose Wan 3.0 when your brief depends on the relationship between references, story progression, and sound. Evaluate the complete sequence, including its final moments.
Pollo API gives your team one integration for image and video models, making it practical to generate reference artwork and develop motion within one application.
Try Wan 3.0 on Pollo API with a recurring character and a simple narrative, then refine the transition that matters most to your story.
Wan 3.0 API FAQs
What is Wan 3.0?
Wan 3.0 is Alibaba’s video generation model for text, image, and reference-based creation. Its capabilities include native sound and longer sequences, with editing and extension described in Alibaba’s documentation.
Can I use existing creative assets with Wan 3.0?
Yes. Reference workflows let existing material guide generation. Specify the role of each asset and check the selected Pollo mode for accepted media types and combinations.
Can Wan 3.0 generate sound with the video?
Yes. Native audio generation supports sound alongside the visuals. In your brief, distinguish spoken words, environmental sounds, and music so the intended audio hierarchy is clear.
How should I compare Wan 3.0 with Wan 3.0 Prime
Test both with the same references and story brief. Compare continuity, sound, completion time, and current pricing; the Prime name alone does not establish a universal quality advantage.
Why run Wan 3.0 through Pollo API?
Pollo API gives one integration for Wan 3.0 and 300+ other models, with documentation, task tracking, webhooks, and lower-cost generation than comparable providers.
