Compare the workflows
| Template in the library | Layout | What to inspect |
|---|---|---|
| INS-style selfie / INS风格自拍生成 | 8 nodes: 5 image, 2 text and 1 video. | The intended identity, portrait direction and sample media before motion. |
| Animate a character / 让TA动起来 | 9 nodes: 7 image, 1 text and 1 video. | The selected pose, scene and character appearance. |
| Shot Size Control / 景别控制拍摄片段 | 8 nodes: 2 image, 5 text and 1 video. | Distance, viewpoint and framing before the video step. |
1. Portrait direction: the INS-style selfie layout
Find the portrait template by its library label, INS风格自拍生成. Its layout contains image and text stages for a selfie-style direction, a supplied character reference and a video stage. Use it when you want to establish an appearance before developing a short social-video idea.
Inspect every sample input and replace it with your own fictional character or material you have permission to use. Check intermediate portrait results rather than assuming the final video node establishes identity. The existing example is not evidence of a real endorsement or of your own completed generation.
2. Movement planning: the Animate a Character layout
Find 让TA动起来 in the library. Its layout includes a character image, pose images, a scene-extraction step, an image-composition step and one video node. The visible video direction is a short boxing action, so this is a motion-planning example rather than a passive talking portrait.
Choose the pose that fits the intended action and inspect the composition before motion. Review the full body, hands and background when the result returns. A template containing several pose images does not establish that every pose is connected or consumed by every subsequent generation.
3. Framing decisions: the Shot Size Control layout
Find 景别控制拍摄片段, shown as Shot Size Control in the canvas quick-start selection. This layout combines an image reference, text controls for shot decisions, a generated image stage and a video stage. Use it when distance or viewpoint is the decision you want to isolate.
Choose one framing change and inspect the new still before proceeding to video. Compare the face, clothing and scene with the approved reference. Do not treat a camera instruction or a text control as proof that the selected model will reproduce an exact lens or movement.
4. Open, inspect and adapt the template
Open the canvas workspace, sign in when needed, and create or open your canvas. Use the Templates control and search for the library label above. Inspect the template details before applying it; quick-start cards show only a selection of the full library.
These reference graphs were reconstructed from visible TapNow template pages, as recorded by the existing library. Sample previews depend on the original external source and are not Omni AiLab generation evidence. This guide describes the inspected layout and provides newly written brief examples; it does not republish the original preview media or claim ownership of its results.
See the saved workflow
Compare a reference, the saved previews and the settings in a related public template walkthrough.
- Animate a character from a pose reference: a short-video workflow
Explore a public character-animation template with a portrait, pose guide, composite still and five-second action preview, plus review checks.
Prompt examples to adapt
These prompts illustrate a creative brief. They are not claims about a measured generation result; adapt them to your reference and the model controls available in the app.
Adapt the portrait direction
Prepare a selfie-style portrait direction for my approved adult fictional character. Soft daylight, a simple room and a relaxed expression. Keep the hairstyle and clothing consistent with my own reference. Review the portrait before planning a short motion.
A new example brief for adaptation; replace the library sample inputs first.
Adapt the motion plan
Using my approved adult character and pose reference, prepare a clear full-body composition for one restrained practice movement. Keep the scene quiet and the full limbs visible. Inspect the still for anatomy and wardrobe before choosing a video action.
This illustrates preparation; it does not assert a result from the motion template.
Adapt shot-size control
Use my approved character image to prepare a medium shot at eye level. Keep the hairstyle, wardrobe and light direction unchanged. Change only the framing first, leaving clear space around the shoulders for a later slow head turn.
Inspect the actual model and reference controls; a written instruction is not a consistency guarantee.
When a result needs another pass
The quick-start page does not show all three templates
Open the Templates control inside a canvas and search the full library by the labels in this guide.
A sample preview is missing or different
The reference library uses externally hosted samples. Replace those samples with your own approved inputs and verify the selected settings.
The template includes a model or setting that is unavailable
Review the current model choices and supported inputs in the creation tool before running a step. Do not assume stored settings are current availability.
Before the next creation step
- The selected template matches the next creative decision.
- Sample inputs have been inspected and replaced.
- The actual selected references and model controls are understood.
- A generated result will be reviewed separately from the sample preview.
Prepare a character direction · Review video creation inputs · Open the canvas workspace
Reading this guide does not start a generation. Sign in and review the selected model, settings and quote in the creation tool when you are ready.
Workflow guidance is compiled from the creation tools currently available in Omni AiLab. Controls and availability can change; the current interface is the reference for a specific task.