Prompts
Featured
Models
Submit
Blog

AhaPrompt

AI Prompts for Images, Video & Audio — Every Model, One Library

Explore

All Prompts
Featured Prompts
Image Prompts
Video Prompts
Audio Prompts
AI Models
Submit a Prompt
Blog

Languages

English
中文
日本語
한국어

Copyright © 2026 AhaPrompt All rights reserved.

Privacy Policy Terms of Service

HomeAI Prompt LibraryAI Video PromptsLive2D VTuber Avatar Rigging Guide

Live2D VTuber Avatar Rigging Guide

GPT-6 AstraOpenAIvideo

Help me turn this character into a Live2D avatar for VTube Studio and OBS. Let’s approve the design first, prepare properly separated artwork with hidden overlap, then build and test the rig in stages. Keep versioned backups and explain what you can automate with the tools available.

Details

Type: AI Video Prompts
Aspect Ratio: 16:9
Duration: 1:31
Updated: Sep 14, 2026

Category

Character Anime Game Assets

How to use this prompt

1Copy the full prompt with the copy button above.
2Open GPT-6 Astra by OpenAI, or your preferred AI video generator.
3Paste the prompt and keep the camera and motion terms — they steer the cinematography.
4Match the example's settings (16:9 · 1:31 · Character · Anime · Game Assets), then iterate — small wording changes shift the output a lot.

Frequently asked questions

Which AI model generated this video?

This clip was generated with GPT-6 Astra by OpenAI. The prompt on this page is the exact text used to create it.

What settings does this prompt use?

The example was generated with GPT-6 Astra using: 16:9 · 1:31 · Character · Anime · Game Assets. Reusing these settings gives the closest match.

How do I get similar results?

Copy the prompt as-is first, then change the subject while keeping the camera, motion, and lighting terms. Video models are sensitive to wording, so expect a few runs.

Can I modify this prompt?

Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.

More GPT-6 Astra prompts

[Reference Image Definition] Image1 = Red-dressed ethnic-style cartoon girl | Sole character reference Image1 is the only and highest-priority reference for the character's identity, face, hairstyle, clothing, and art style throughout the entire video. Throughout the entire video, strictly maintain the girl from Image1: Recognizable facial features Facial feature proportions Black double braids Red-and-blue braided hair decorations Ethnic-style headpiece Earrings Red ethnic-style long dress Clothing patterns and fur-trimmed decorations Brown short boots Soft, delicate 2D anime illustration texture Cute, lively, with a slightly playful and mischievous vibe Prohibited: Photorealistic rendering 3D rendering Turning into someone else Changing hairstyle Changing clothing Changing art style Image2 = X profile page screenshot | Sole background and layout reference Image2 is the sole reference for the background, UI, typography, and composition of the entire video. Strictly maintain from Image2: Top banner image Position of the circular avatar frame White UI background All buttons Icons Page structure Whitespace Colors Proportions Throughout the entire video, the camera is completely fixed. Any of the following is prohibited for the entire page: Zooming Panning Rotation Perspective changes Recomposition Except for the specified performance, the UI and background must not change. [Overall Requirements] Generate a 15-second, 9:16 vertical, fixed-camera, 2D cartoon-animation-style short video. Throughout the entire video: The background is always the X profile page screenshot from Image2 Only the character and the text being manipulated move The character is initially located inside the circular avatar frame The character's appearance must be replaced with the red-dressed ethnic-style cartoon girl from Image1 The circular avatar frame position and the page itself remain unchanged at all times The overall rhythm is light, clear, with a touch of comedy No dialogue No narration No speech bubbles No additional subtitles No new unrelated characters No new unrelated logos No new unrelated text [Timeline Action Design] [0.0–2.3 seconds] The entire X page remains completely fixed. Only the inside of the circular avatar frame begins to move. The red-dressed girl inside the circular frame first blinks gently, revealing a sweet smile. She slightly lowers her head to adjust her cuffs, then gently lifts the edge of her skirt, as if preparing to make an entrance. Then she looks up at the page outside, glances down at the text content on the page, and finally looks back at the camera, a playful "up to mischief" smirk slowly spreading across her lips. Movements are small, natural, cute, and lively. No exaggerated distortion. No large swinging motions. [2.3–4.0 seconds] The girl places both hands on the edge of the circular avatar frame, treating it as a small entrance, and naturally climbs out from inside it. The sequence of actions is clearly shown as: Both hands grip the frame edge Upper body leans out first One foot steps out first The other foot follows She gently lifts her skirt slightly to prevent the long dress from getting caught The skirt hem briefly gets lightly caught on the frame edge She looks back and gently tugs at the skirt hem The skirt comes out smoothly She lands lightly on the white whitespace area below the X page Upon landing, the character should be light and natural, with the skirt, braids, earrings, and headpiece swaying gently and naturally. Only the character comes out of the avatar frame. The circular avatar frame itself remains in place, undeformed, and does not disappear. The page itself must not undergo any structural changes. [4.0–7.6 seconds] After landing, the girl looks around and notices there is a lot of text on the page. She immediately shows a delighted expression of "I've got a mischievous idea." She begins tearing off sections of text from the page one by one. The operable targets are all readable text / letters / numbers within the page, including: Profile name User ID Bio text Join date Following count Follower count Text inside buttons Post content text Other readable text / letters / numbers She tears off text only 3 times, with clear actions and crisp rhythm: 1st tear She walks to the area near the profile name, pinches an entire section of text with two fingers, and clearly peels it off the page surface like a sticker. The torn-off text is quickly folded twice in her hands and instantly becomes a small paper airplane. She flicks her wrist and sends the paper airplane flying toward the camera. The paper airplane passes through the foreground and flies out of frame. The corresponding original text position immediately becomes blank white. 2nd tear She tears off a section of bio text. This time the motion is more practiced — she folds it into a paper airplane quickly while walking. Then she crisply tosses it out toward the other side of the camera. The paper airplane flies across the foreground of the frame. The corresponding text disappears simultaneously, leaving only blank space. 3rd tear She tears off a larger block of text from the post area. This block is somewhat larger, and she quickly folds it into a slightly bigger paper airplane with both hands. She first does a small "ready to throw" motion, then suddenly throws it toward the camera. The paper airplane rapidly grows larger toward the camera, then flies out of frame. The corresponding original text area is completely transformed into blank white space. After the 3rd throw, she proudly claps her hands lightly. Important requirements Text must be lifted and torn off like paper stickers It cannot simply disappear Paper airplanes must be folded from the torn-off text Each time a paper airplane flies away, the corresponding original text position must genuinely become blank Paper airplanes should not be so large as to block the entire frame Only text may be removed The following elements must be preserved: Top banner illustration Circular avatar frame Image areas All graphic icons Button outlines Dividing lines Thumbnails Other non-text visual elements [7.6–10.4 seconds] She looks around the page and notices there is still a lot of residual text. Her proud smile slightly fades, revealing a hint of "how is there still this much" expression. She lightly places one hand on her hip, then produces a simple broom from behind her. Then she performs 3 brisk screen-clearing motions: 1st sweep A horizontal sweep across the upper part of the page. An entire row of residual text slides away like thin scraps of paper. 2nd sweep A diagonal sweep from the middle of the page downward. The remaining text continues to be gathered and pushed toward one side of the page. 3rd sweep A firm but not overly forceful sweep toward the lower right of the page. The last pile of residual text is swept entirely out of frame. After sweeping, she lightly taps the broom handle on the ground once, as if satisfied with the finish. Important requirements Only text touched by the broom may disappear Text must be gathered and swept away following the broom's motion It cannot suddenly disappear without reason The broom may only appear after the paper airplane actions are complete There is only one broom — it cannot multiply After sweeping, all old text on the page must be completely cleared. Only the following remain on the page: Background image UI graphic icons Button outlines Image elements Large areas of clean white whitespace [10.4–13.7 seconds] She leans the broom gently to one side, then looks down and takes out a thick black marker from her outfit. She pops the cap off with a "snap," turns around, and faces the large area of white whitespace that has been cleared. Then, using the thick black handwritten marker, she writes two lines in the large blank area from the center to the lower part of the page: This place belongs to Sun Keke now! Thank you all for liking it These two lines of text must be clearly, accurately, and completely displayed. No typos. No missing characters. No garbled text. No substitution with other sentences. No addition of any other new text. Text style requirements: Black Thick marker handwritten feel Written out stroke by stroke naturally Large enough Clearly legible Occupying a prominent position in the frame The writing process must clearly show the pen tip advancing — the characters are written out stroke by stroke, not appearing instantly. [13.7–15.0 seconds] After writing, she puts the marker cap back on. She takes a small step back and looks at her "masterpiece" with satisfaction. Then she holds the broom with one hand and the marker with the other, slightly turning to the side. She then looks back over her shoulder toward the camera, revealing a slightly smug, cute, and playful mischievous smile. Not an exaggerated laugh, but a gentle eye-squint, the happy smile after a successful prank. Finally, there is a static freeze frame for approximately 0.7 seconds. In the freeze frame, the following must be clearly visible simultaneously: The two lines of large text on the page: This place belongs to Sun Keke now! Thank you all for liking it The red-dressed girl looking back at the camera with a playful smile The broom The X page background with all text cleared

You are given a task to integrate an existing React component in the codebase The codebase should support: - shadcn project structure - Tailwind CSS - Typescript If it doesn't, provide instructions on how to setup project via shadcn CLI, install Tailwind or Typescript. Determine the default path for components and styles. If default path for components is not /components/ui, provide instructions on why it's important to create this folder Copy-paste this component to /components/ui folder: ```tsx mac-book-neo-hero.tsx "use client"; import * as React from "react"; import { useEffect, useRef, useState } from "react"; export type FrameSequenceStep = { from: number; to: number; color: string; num: string; total: string; icon?: React.ReactNode; title: string; description: string; label: string; }; export type FrameSequenceHeroProps = { frameCount: number; framePath: (i: number) => string; eagerCount?: number; scrollHeight?: string; brand?: React.ReactNode; navLinks?: { label: string; href: string }[]; ctaLabel?: string; ctaHref?: string; title: React.ReactNode; subtitle?: string; steps: FrameSequenceStep[]; className?: string; }; const cx = (...c: (string | false | null | undefined)[]) => c.filter(Boolean).join(" "); export function FrameSequenceHero({ frameCount, framePath, eagerCount = 140, scrollHeight = "600vh", brand, navLinks = [], ctaLabel, ctaHref = "#", title, subtitle, steps, className, }: FrameSequenceHeroProps) { const spacerRef = useRef(null); const cacheRef = useRef(new Array(frameCount)); const loadedRef = useRef(0); const targetFrameRef = useRef(0); const displayFrameRef = useRef(0); const lastShownRef = useRef(-1); const rafActiveRef = useRef(false); const [loadPct, setLoadPct] = useState(0); const [loaderDone, setLoaderDone] = useState(false); const [navScrolled, setNavScrolled] = useState(false); const [subHidden, setSubHidden] = useState(false); const [activeIdx, setActiveIdx] = useState(-1); const [progress, setProgress] = useState(0); const [stepLocal, setStepLocal] = useState(0); const [currentSrc, setCurrentSrc] = useState(() => framePath(1)); const showFrame = (i: number) => { if (i === lastShownRef.current) return; setCurrentSrc(framePath(i + 1)); lastShownRef.current = i; }; const loop = () => { if (rafActiveRef.current) return; rafActiveRef.current = true; const tick = () => { const diff = targetFrameRef.current - displayFrameRef.current; if (Math.abs(diff) { const eager = Math.min(eagerCount, frameCount); const loadOne = (i: number) => { const img = new Image(); img.decoding = "async"; img.src = framePath(i + 1); const onSettle = () => { loadedRef.current += 1; const pct = Math.round((loadedRef.current / frameCount) * 100); setLoadPct(pct); if (loadedRef.current === eager) { setLoaderDone(true); for (let j = eager; j { const spacer = spacerRef.current; if (!spacer) return; const total = spacer.offsetHeight - window.innerHeight; const p = Math.max(0, Math.min(1, window.scrollY / Math.max(1, total))); targetFrameRef.current = p * (frameCount - 1); loop(); setProgress(p); setNavScrolled(window.scrollY > 4); setSubHidden(window.scrollY > 8); let idx = -1; let local = 0; for (let i = 0; i = s.from && p { window.addEventListener("scroll", onScroll, { passive: true }); window.addEventListener("resize", onScroll); onScroll(); return () => { window.removeEventListener("scroll", onScroll); window.removeEventListener("resize", onScroll); }; // eslint-disable-next-line react-hooks/exhaustive-deps }, [steps, frameCount]); return ( {loadPct {brand} {navLinks.length > 0 && ( {https://t.co/tSkQpsSthN((l) => ( {l.label} ))} )}

【Reference Image Definition】 Image1 = Li Jiuer chibi character | Sole character reference Image1 is the sole and highest-priority reference for the character's identity, face, hairstyle, outfit, and art style throughout the entire video. Throughout the entire video, strictly maintain from Image1: Recognizable facial features Facial feature proportions Short hair Black-rimmed glasses Dark short-sleeved top Dark long pants Black shoes Flat, clean cartoon illustration texture A rational, relaxed, slightly humorous temperament Prohibited: Realistic humanization 3D-ification Turning into someone else Changing hairstyle Changing outfit Changing art style Image2 = X personal profile screenshot | Sole background and layout reference Image2 is the sole background, UI, typography, and composition reference for the entire video. Strictly maintain from Image2: Top banner image Position of the circular avatar frame White UI background All buttons Icons Page structure Whitespace Colors Proportions Throughout the entire video, the camera is completely fixed. The X personal profile remains front-facing, horizontal, full-screen, and fixed from the first frame to the last frame, with all four edges of the page always parallel to the video frame. Any of the following operations on the entire page are prohibited: Scaling Panning Rotating Tilting Perspective changes Recomposition The entire profile page tilting left or right is prohibited. The page shrinking to reveal new external gray background is prohibited. Except for the specified performance, the UI and background must not change. 【Overall Requirements】 Generate a 15-second, 9:16 vertical, fixed-camera, 2D cartoon animation style short video. Throughout the entire video: The background is always the X profile screenshot from Image2 Only the character and the text being manipulated move The character initially appears inside the circular avatar frame The character's appearance must be replaced with the Li Jiuer chibi character from Image1 The circular avatar frame position and the page itself remain unchanged at all times The overall rhythm is light, clear, with a touch of comedy No dialogue No narration No speech bubbles No additional subtitles No new unrelated characters No new unrelated logos No new unrelated text 【Timeline Action Design】【0.0–2.3 seconds】 The entire X page remains completely fixed. Only the inside of the circular avatar frame begins to move. Li Jiuer inside the circular frame first blinks slightly, with a calm and natural expression. Then he glances around at the page, raises a hand to gently push up his glasses. Then he looks down at the text content on the page, as if observing this profile, and finally looks back at the camera, with a faint smile on his lips that says "I've got an idea." The movements are natural, restrained, and crisp. No exaggerated distortion. No large swinging motions. 【2.3–4.0 seconds】 Li Jiuer places both hands on the edge of the circular avatar frame, treating it as a small entrance, and naturally climbs out from inside. The sequence of actions is clearly shown as: Both hands grip the frame edge Upper body leans out first One foot steps out first The other foot follows He naturally emerges from the avatar Finally arriving on the white whitespace area below the X page When landing, the character's movements must be natural and nimble, with slight natural follow-through motion in the arms, body, and glasses. Only the character comes out of the avatar. The circular avatar frame itself remains in its original position, without deformation or disappearing. The page itself must not undergo any structural changes. Throughout the entire process, the X personal profile remains front-facing, horizontal, and full-screen fixed, not allowed to tilt left or right, with no perspective changes. 【4.0–7.6 seconds】 After landing, Li Jiuer looks around left and right, notices there is a lot of text on the page, and immediately shows a relaxed expression of "time to start tidying up." He begins tearing off sections of text from the page one by one. The operable objects are all readable text / letters / numbers on the page, such as: Profile display name User ID Bio text Join date Following count Follower count Text inside buttons Post content text Other readable text / letters / numbers Only 3 tearing actions, with clear movements and crisp rhythm: Action 1 He walks near the page name area, pinches an entire section of text with two fingers, and clearly tears the text off the page surface like peeling off a sticker. The torn text instantly transforms into a small sticky note card in his hand. He holds the card between two fingers and, like flicking a playing card, crisply flicks the card toward the camera. The card sweeps past the foreground and flies out of frame. The corresponding original text position immediately becomes white blank space. Action 2 He tears off a section of bio text. This time the movement is more practiced — as he walks, the torn text transforms into a sticky note card. Then he crisply flicks it out toward the other side of the camera. The card flies across the foreground of the frame. The text at the corresponding position disappears simultaneously, leaving only blank space. Action 3 He tears off a larger block of text from the post area. This block is slightly larger and transforms into a slightly bigger sticky note card. He first does a small "getting ready to flick" motion, then suddenly flicks it toward the camera. The card rapidly grows larger toward the camera, then flies out of frame. The corresponding original text area is completely turned into white blank space. After the third flick, he lightly claps his hands once in satisfaction. Important requirements Text must be lifted and torn off like paper stickers It cannot simply disappear Sticky note cards must be formed from the torn-off text Each time a sticky note card is flicked away, the corresponding original text position must genuinely become blank Sticky note cards must not be so large as to block the entire frame Only text removal is allowed The following elements must be preserved: Top banner illustration Circular avatar frame Image areas All graphic icons Button outlines Dividing lines Thumbnails Other non-text visual elements 【7.6–10.4 seconds】 He looks around the page and notices there is still residual text remaining. His relaxed expression slightly tightens, showing a look of "there's still quite a bit left." He takes out a simple roller / squeegee / whiteboard eraser from behind him. Then he performs 3 brisk screen-clearing actions: Action 1 A horizontal wipe across the upper part of the page. An entire row of residual text is carried away like thin sheets of paper. Action 2 A diagonal wipe from the middle of the page downward. The remaining text continues to be gathered and piled toward one side of the page. Action 3 A clean finishing sweep toward the lower right of the page. The last pile of residual text is completely cleared out of frame. After cleaning is done, he lightly stows away the tool, as if finishing with satisfaction. Important requirements Only text touched by the roller / squeegee / whiteboard eraser disappears Text must be gathered and swept away following the tool's motion Text cannot suddenly disappear without reason The tool may only appear after the sticky note card actions are complete There is only one tool, and it cannot multiply After cleaning, all old text on the page must be completely cleared. Only the following remains on the page: Background image UI graphic icons Button outlines Image elements Large areas of clean white whitespace During the cleaning process, the entire X page itself must absolutely not move, tilt, or rotate. 【10.4–13.7 seconds】 He sets the tool aside gently, looks down, and takes out a thick black marker from his person. He snaps the cap off the marker with a "pop," turns around to face the large white whitespace area after clearing. Then Li Jiuer, the animated character himself, personally writes by hand. Using the thick black handwritten marker, in the large blank area from the center to the lower part of the page, he writes two lines: This place belongs to Li Jiuer now! Welcome to chat about AI These two lines of text must be clearly, accurately, and completely displayed. No typos allowed. No missing characters allowed. No garbled text allowed. No substitution with other sentences allowed. No addition of any other new text allowed. Text style requirements: Black Thick marker handwritten feel Naturally written stroke by stroke Large enough Clear and legible Occupies a prominent position in the frame The writing process must clearly show the marker tip advancing — the characters are written stroke by stroke, not appearing instantly. The person writing must be Li Jiuer himself. The hand writing must be the character's own hand. Any off-screen hand, floating hand, or real hand is prohibited. 【13.7–15.0 seconds】 After writing, he puts the marker cap back on. He takes a small step back and looks at his "masterpiece" with satisfaction. Then he naturally holds the marker in one hand and turns slightly to the side. He then turns his head toward the camera, gently pushes up his glasses, and reveals a faint, relaxed smile with a hint of confidence. Not an exaggerated laugh, but a natural, relaxed, satisfied-after-writing expression. Finally, there is a static freeze frame for approximately 0.7 seconds. In the freeze frame, the following must be clearly visible simultaneously: The two large lines of text on the page: This place belongs to Li Jiuer now! Welcome to chat about AI Li Jiuer looking at the camera, lightly pushing his glasses, with a faint smile The X page background with text cleared away 【Mandatory Constraints】 Use only the two reference images Image1 and Image2 Image1 is the sole character reference Image2 is the sole background / UI / layout reference The camera is completely fixed throughout The X personal profile remains front-facing, horizontal, and full-screen fixed from the first frame to the last frame All four edges of the page remain parallel to the video frame at all times The entire profile page tilting left or right is prohibited The page shrinking to reveal new external gray background is prohibited Do not alter the original screenshot composition, top banner, or UI positions Do not delete text prematurely The first half must be "tear text → transform into sticky note card → flick toward camera" The middle section must use a roller / squeegee / whiteboard eraser to clean up remaining text The tool may only appear after the sticky note card actions are complete Only after cleaning is done may the marker be brought out All old text must ultimately disappear completely Only delete text — do not delete images, icons, buttons, borders, lines, or other non-text elements The final page retains only the two newly written lines: This place belongs to Li Jiuer now! Welcome to chat about AI Maintain Image1 character's face, glasses, hairstyle, outfit, art style, and illustration texture No realistic humanization No 3D-ification No turning into someone else No adding extra characters No adding extra arms, fingers, or legs No duplicate generation of tools or markers No off-screen hands helping to write The animated character must write by himself No generating new logos or unrelated text No garbled text No dialogue No narration No speech bubbles

A mission-game loadout experience where you can rotate a character, switch between male and female operators, change skin tone, try different uniforms, helmets, boots and weapons, then make the character stand, walk or run.

A house cat sits in front of an empty gilded mirror. A full-size lion slowly materializes inside the glass. The magician throws a blue velvet cloth over the entire frame. The cloth drops: the mirror has vanished, and the lion is standing onstage. Final frame: the lion calmly lies down beside the cat.

Generate a hyper-realistic GTA 6-style Bangalore street in Three.js from an iPhone POV.

rebuild the town as individual 3D objects, rig the bunny with a simple 20-bone skeleton, move it between two locations, and have the camera follow.

Create a cozy lake with a fisherman’s cabin on the marshy shore. Put a small island in the middle of the water, with an abandoned house hidden among the trees. Add a fishing boat beside the cabin, lily pads, reeds, jumping fish, typical wetland wildlife, a small beach, one path leading to the beach and cabin, another path returning into the forest, and a tree line around the entire scene.

Browse all GPT-6 Astra prompts Explore AI Video Prompts