What should I upload for a frame-based video?

Use a clear first frame, and add a last frame when you want to describe an endpoint. Keep the subject and intended transition understandable in the prompt.

Can I combine every kind of reference?

Not every combination is accepted. A reference link and reference file cannot be used together, and neither can be combined with first/last frames. Choose one coherent input workflow.

How do I choose duration and resolution?

The visible choices are 5–30 seconds in five-second steps and 480p, 720p or 1080p. Match the shot to its destination and review the generator’s current credit estimate.

What should I upload for a frame-based video?

Use a clear first frame, and add a last frame when you want to describe an endpoint. Keep the subject and intended transition understandable in the prompt.

Can I combine every kind of reference?

Not every combination is accepted. A reference link and reference file cannot be used together, and neither can be combined with first/last frames. Choose one coherent input workflow.

How do I choose duration and resolution?

The visible choices are 5–30 seconds in five-second steps and 480p, 720p or 1080p. Match the shot to its destination and review the generator’s current credit estimate.

Wan 3.0 Video: Build a Shot on GPTImage

Turn a scene brief into a Wan 3.0 video

Choose Wan 3.0 Video in the GPTImage generator, describe one clear scene, then decide how your images, reference clips and sound should guide it.

About

About Wan 3.0 Video

Wan 3.0 Video is the standard Wan 3.0 model available in GPTImage’s video workspace. Begin with a written scene, animate an image, or use reference material to explain the appearance and movement you want. The same workspace lets you review the selected model, upload status, output settings and credit estimate before submitting. This page describes that standard model’s current controls.

Plan your Wan 3.0 shot

From source material to a finished clip

Core Features Overview

Write a shot that can be followed

Describe the subject, its action, the setting and a camera move. A shop-window reflection at dusk needs a different brief from a product rotating on a table. Keep the sequence readable rather than placing several unrelated scenes in one request. Use the text workflow when you want the description to establish the shot.

Give each reference a clear role

An image can establish a starting composition; first and last frames can describe the intended transition. Reference mode accepts up to ten images, with video and audio inputs also available. Explain what each asset contributes instead of expecting every detail to carry over unchanged. Wait until uploads finish before reviewing the request.

Choose the frame before generating

GPTImage offers 480p, 720p and 1080p, with durations of 5, 10, 15, 20, 25 or 30 seconds. Choose adaptive framing or 16:9, 4:3, 1:1, 3:4 or 9:16 for the screen you plan to use. Leave enough time for the action and check the current estimate with those settings selected.

Review motion and sound together

Sound generation can be switched on or off. If audio matters, describe the intended atmosphere alongside the visual action, then watch and listen to the completed clip. Check subject details, motion, framing and timing before using it in an edit. Adjust one part of the brief at a time when exploring another version.

Wan 3.0 Video questions

Turn a scene brief into a Wan 3.0 video FAQ

Open the video generator and select Wan 3.0 Video. Choose the appropriate text, image or reference workflow, then confirm the model name and settings before submitting.

Explore More AI Video Models

Veo 3.1

New

Veo 3.1 represents Google DeepMind's most advanced AI video generation technology, featuring groundbreaking native audio generation that creates synchronized sound effects, dialogue, and environmental audio alongside video content.

Try now

Wan 2.6

New

Wan 2.6 is Alibaba's video generation model delivering high-quality videos with diverse style support, smooth motion, and cinematic output from text prompts and reference images.

Try now

Sora 2

Sora 2 is OpenAI's flagship video generation model capable of producing high-quality videos from both text descriptions and image inputs. It understands complex scene compositions, character interactions, camera movements, and real-world physics to deliver cinematic results. Sora 2 represents a major leap in AI video generation with improved temporal consistency, longer duration support, and more faithful prompt interpretation.

Try now

Vidu Q4 Video Generator

New

Vidu Q4 is a video model developed by ShengShu Technology. Image-to-video turns one image into a 3–16 second clip, while reference-to-video combines 1–15 images into a 3–16 second clip. Optional audio and up to three voice references let you explore scenes in which appearance, movement and sound work together.

Try now

Kling 2.6

Kling 2.6 is Kuaishou's latest AI video generation model, recognized for its exceptional motion quality and cinematic output. Built on advanced spatiotemporal modeling, Kling 2.6 produces videos with fluid character movement, dynamic camera transitions, and rich visual detail. It supports both text-to-video and image-to-video generation, making it a versatile tool for creators seeking professional-quality AI video content.

Try now

Seedance 2.0

New

Seedance 2.0 is ByteDance's most advanced AI video generation model, unveiled in February 2026. It adopts a unified multimodal audio-video joint generation architecture supporting 4 input modalities simultaneously — text, up to 9 images, up to 3 video clips, and up to 3 audio tracks. The ground-breaking @-reference system lets you tag specific elements in your prompt and bind them to uploaded references for granular control over camera movement, character appearance, audio rhythm, and visual style. Outputs reach up to 2K resolution with native synchronized audio including multilingual lip-sync, sound effects, and background music.

Try now

Prepare your next scene

Select Wan 3.0 Video, finish uploading your inputs and review the settings before generating.

Create with Wan 3.0

+1k