Use this Skill when the user wants a finished 15-second, 16:9 live-action-and-hand-drawn fusion video. The output must preserve the structure: a flat hand-drawn luminous animation appears in a real space, clearly contacts live-action hands or objects in the first 0-3 seconds, continuously morphs as one single entity, escapes, and a handheld phone camera follows slightly late.
This Skill organizes the prompt in the user input language and recommends MiniMax H3 as the confirmed generation step. Do not generate video until the user explicitly confirms H3 generation. Do not route to planner or executor for prompt-writing. The final prompt language must follow the dominant language of the user input: Chinese input produces Chinese, English input produces English, Japanese input produces Japanese; for mixed input, use the dominant language; when unclear, use the current conversation language. Only user-required proper nouns, model names, or literal parameters may remain unchanged.
Step 1: Understand the user intent as same-language constraints
When the user provides any language, understand it as the following workflow requirements and express the final prompt in the dominant language of the user input:
- Create a completely new 15-second video generation prompt based on the reference prompt, without superficially imitating the original sentences.
- The visual structure must be preserved: a flat hand-drawn glowing animation appears in a live-action space; the animation makes contact with a real hand or real object; the same entity continuously transforms and escapes; the camera always chases half a beat late.
- The hand-drawn animation texture must feel like crayon, chalk, colored pencil, pastel, or rough brush; the lines tremble slightly, with uneven smudging, rough edges, and a frame-by-frame redrawn feel.
- 3DCG, plush-toy feel, uniform vector lines, smooth neon, horror monsters, giant eyes, split mouths, teeth, intimidation, pouncing bites, sudden black screens, and jump scares are prohibited.
- From 0-3 seconds, there must be clear contact between the live-action hand and the hand-drawn animation, for example wrapping around a finger, landing in the palm, escaping when grabbed, or being born from a fingertip.
- The animation must continuously transform as the same entity, and may change between forms such as "lines, creatures, marks, plants, vehicles, small everyday objects," while retaining traces of the previous form.
- Suddenly introducing another completely new character is not allowed.
- The whole film must unfold continuously in the same space or an adjacent range, without cuts jumping to another location, as if the shooter is truly walking and chasing.
- Each interval 0-3, 3-6, 6-10, 10-13, and 13-15 seconds must have a new transformation, movement, contact, discovery, prank, or surprise.
- The shooter must also participate: reaching out, grabbing, chasing, opening a door or box, catching, backing away, being pranked, and so on.
- The tone is cute, slice-of-life, nostalgic, gentle, and slightly bittersweet, not horror comedy.
- From 13-15 seconds, there must be a space-level transformation: the previous lines spread to walls, floor, ceiling, windows, sink, or passage, becoming giant flowers, starry sky, sunset, clouds, ribbons, a graffiti town, etc.; the ending must have a moving afterglow and a little cute punchline.
Step 2: Invent all creative content fresh
For every run, create a new combination. Do not reuse the reference prompt's dark room, PC, fridge, stars, hearts, blue vortex, butterfly, snake, octopus, hamburger, giant eye, teeth, or dark ending.
Choose new values for all of these:
- Live-action space, but still a slice-of-life and continuously trackable adjacent range;
- hand-drawn entity or initial form;
- central color;
- continuous transformation chain;
- the way it makes contact with a real hand or real object;
- the chase route through the space;
- the shooter's reaction;
- the final space-level transformation and cute punchline.
Good example directions include: rainy-day kitchen sink, old balcony laundry corner, early-morning entryway, small bookstore corridor, small table by a train window, bathroom medicine cabinet, craft table, greenhouse passage, laundromat bench, old dining table. Use only one or adjacent connected areas.
Step 3: Required output format
The final prompt must begin with a sentence pattern matching the dominant language of the user input. For Chinese input, use this pattern:
15秒，16:9横版视频。将实拍的〇〇与手绘发光动画融合的影像。
Replace “〇〇” with the newly invented live-action space or everyday scene. For non-Chinese input, use an equivalent opening in the same language and include duration, 16:9 landscape format, live-action space, and hand-drawn glowing animation fusion.
Do not add titles, auxiliary headings such as 舞台设置 or 色味, or explanatory notes. Keep this paragraph order:
- opening sentence;
- live-action space and phone-shot texture;
- 0-3 seconds;
- 3-6 seconds;
- 6-10 seconds;
- 10-13 seconds;
- 13-15 seconds;
- hand-drawn texture;
- camera follow method;
- prohibited items;
- ambient sound.
Step 4: Prompt writing rules
- Keep the prompt executable as a video-generation prompt, not an essay.
- Unless the user asks for explanation, the final answer should contain the prompt text in the dominant language of the user input first, followed by one short next-step recommendation in the same language.
- The recommendation must invite the user, in the same language, to use MiniMax H3 to generate a 15-second 16:9 video from this prompt. Chinese example:
下一步建议：如果你确认这个 prompt，我可以继续用 H3 模型生成 15 秒 16:9 视频。 - Do not generate a video, image, audio, storyboard, or intermediate asset until the user explicitly confirms the H3 generation step.
- Mention Seedance only as a target usage context when the user asks; do not add model parameters inside the creative prompt unless requested.
- The first 0-3 seconds must make real/hand-drawn fusion obvious through contact.
- The camera must not neatly center the animation. It should lag behind, pan/tilt/advance after the entity already leaves the frame edge.
- The entity should remain traceable: each new form preserves a line, tail, color smear, body curve, or motif from the previous form.
- Use soft, emotional, comic, cute beats: tiny stumbles, shy gestures, a dot falling behind, a petal sticking to lens, a star dropping into a palm, confetti sneeze, one small creature lagging behind.
- Avoid any horror-coded anatomy or threatening motion.
- The final prompt must not randomly mix in vocabulary, transition sentences, or writing systems from outside the user input language; when the user input language is Japanese, natural Japanese is allowed.
Step 5: Delivery
Output the final prompt in the dominant language of the user input first. After the prompt, add exactly one short same-language recommendation line inviting the user to continue with MiniMax H3 video generation. Do not include a title, checklist, model call summary, filename, or canvas delivery note. If the user later confirms H3 generation, generate the 15-second 16:9 video with MiniMax H3 and check that the result preserves contact, continuous morphing, delayed camera chase, and non-horror hand-drawn texture.