Back to Details

anime-soccer

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

anime-soccer

动漫足球（anime-soccer）

Turn the user into the hero of a 3-scene (~45s) Japanese-anime football short, but the star is the person running it. Each scene is a 15s cel-shaded anime beat with the user (named, in CAPS) and Japanese dialogue, generated on Seedance off an anime character sheet made from the user's photo, then stitched.
The proven pipeline (do not deviate from the order): 
user photo → anime CHARACTER SHEET (nano-banana-pro) → DESIGN the dramatic match + WRITE 3×15s scene prompts (you, acting as Claude) → SEEDANCE each scene off the sheet → STITCH
.
The magic is in three things, in this order: (1) a character sheet so the user's anime likeness is consistent across every scene, (2) a specific, dramatic match designed for them (their team vs the opponent, real kit colors, a concrete goal mechanic each scene — not a generic "he scores"), (3) the scene-prompt formula (cel-shaded style tag + named hero in CAPS + camera/anime techniques + Japanese VO).
将用户打造为3幕（约45秒）日式动漫足球短片的主角，而核心就是使用该流程的用户本人。每一幕都是15秒的赛璐珞风格动漫片段，主角为用户（姓名大写）并配有日语台词，基于用户照片生成的动漫角色表，通过Seedance生成各场景视频后拼接成片。
经过验证的流程（请勿打乱顺序）： 
用户照片 → 动漫角色表（nano-banana-pro）→ 设计戏剧性比赛 + 撰写3×15秒场景提示（由你以Claude身份完成）→ 通过Seedance基于角色表生成各场景视频 → 拼接成片
核心亮点有三点，按顺序为：(1) 角色表确保用户的动漫形象在所有场景中保持一致；(2) 为用户量身设计具体且富有戏剧性的比赛（用户支持的球队对阵对手，真实球衣配色，每个场景都有明确的进球机制——而非笼统的“他进球了”）；(3) 场景提示公式（赛璐珞风格标签 + 大写姓名的主角 + 镜头/动漫手法 + 日语配音）。

Stage 0 — Intake

阶段0 — 信息收集

Collect, in one pass (the only things that change per user):
  • The user's photo (required) — a clear face photo; this becomes the anime hero. Local path or URL. Likeness comes from this. Upload local files via 
    upload_asset
    → use the 
    public_url
    . (If on Claude Desktop where pasted images don't reach MCP, ask once for a URL or a 
    .zip
    .)
  • On-screen hero name (optional) — what to call them in CAPS in the prompts + Japanese VO (e.g. "KAITO"). Default to their first name, or "THE STRIKER" if they'd rather not use a name.
  • Their team (required) — the hero's side. Capture the kit colors / stripe pattern (e.g. "sky-blue and white vertical stripes"), NOT the crest or sponsor (describe colors, not trademarks — see de-branding in failure modes).
  • The opponent (required) — who they're playing against. Capture the opponent's kit colors too. Opponent players (keeper, a defender) are generic — described by kit color, not named.
Confirm in one line ("Putting YOU in an anime match — [TEAM] vs [OPPONENT], you score the winner…"), then run the pipeline. No further yes/no gates.
一次性收集以下信息（每个用户的唯一变量）：
  • 用户照片（必填）——清晰的面部照片；将作为动漫主角的原型。支持本地路径或URL。形象相似度完全基于此照片。本地文件需通过
    upload_asset
    上传→使用生成的
    public_url
    。（若在Claude Desktop中粘贴的图片无法传递至MCP，可要求用户提供URL或
    .zip
    压缩包。）
  • 屏幕显示的主角姓名（可选）——提示语及日语配音中使用的大写姓名（例如“KAITO”）。默认使用用户的名字，若用户不愿透露姓名则默认使用“THE STRIKER”。
  • 用户支持的球队（必填）——主角所属球队。需记录球衣配色/条纹样式（例如“天蓝色与白色竖条纹”），而非队徽或赞助商（仅描述颜色，避免提及商标——详见故障排查中的去品牌化部分）。
  • 对手球队（必填）——对阵的球队。同样需记录对手的球衣配色。对手球员（门将、后卫）为通用形象——仅通过球衣颜色描述，不命名。
用一句话确认（“将你置入动漫比赛——[支持球队]对阵[对手球队]，你将打入绝杀球……”），随后启动流程。无需额外的确认环节。

Stage 1 — Anime character sheet (
generate_image_edit
, nano-banana-pro)

阶段1 — 动漫角色表（
generate_image_edit
，nano-banana-pro）

Generate ONE anime character sheet of the user from their photo. The sheet (multiple angles + full body + close-ups) is what keeps the face consistent across all three scenes.
Call 
generate_image_edit
with:
  • provider
    : 
    nano-banana-pro
     (REQUIRED default). It does reference-identity → anime stylization cleanly for any real face. Don't use 
    gpt-image-2
     here — OpenAI's safety system rejects anime-editing a real photo of an identifiable person (
    content_policy
    / 
    image_generation_user_error
    ).
  • images
    : 
    [<the user's photo url>]
  • aspect_ratio
    : 
    16:9
    · 
    quality
    : 
    high
    · 
    output_format
    : 
    png
  • prompt
    (verbatim template — fill 
    {NAME}
    ; put them in their team kit): 
    Create a character sheet of this football player named {NAME} in a {TEAM kit colors} kit, with close-ups and full body shots from different angles in Japanese anime style.
Save the returned URL as 
state.sheets[HERO]
. Inspect: the sheet must be clearly that person, anime-styled, with usable full-body + face angles. Re-roll if it drifts. (If the user also wants a named teammate/rival on screen with a real face, make a sheet per character the same way; otherwise opponents stay generic.)
基于用户照片生成一张动漫角色表。该角色表包含多角度特写及全身照，用于确保所有场景中用户的面部形象保持一致。
调用
generate_image_edit
时需设置：
  • provider
    ：
    nano-banana-pro
    （必填默认值）。它能精准地将真实面部转化为动漫风格，且效果稳定。请勿使用
    gpt-image-2
    ——OpenAI的安全机制会拒绝对可识别的真实人物照片进行动漫化编辑（触发
    content_policy
    / 
    image_generation_user_error
    ）。
  • images
    ：
    [<用户照片的URL>]
  • aspect_ratio
    ：
    16:9
    · 
    quality
    ：
    high
    · 
    output_format
    ：
    png
  • prompt
    （严格使用模板——替换
    {NAME}
    ；让主角身着支持球队的球衣）： 
    Create a character sheet of this football player named {NAME} in a {TEAM kit colors} kit, with close-ups and full body shots from different angles in Japanese anime style.
将返回的URL保存为
state.sheets[HERO]
。检查：角色表需清晰呈现用户的动漫化形象，包含可用的全身照及面部特写角度。若形象偏差需重新生成。（若用户希望屏幕中出现带有真实面部的指定队友/对手，需为每个角色按相同方式生成角色表；否则对手保持通用形象。）

Stage 2 — Design the match + write the 3 scene prompts (you = "Claude")

阶段2 — 设计比赛 + 撰写3幕场景提示（你以“Claude”身份完成）

This is the step the creator did in Claude. You do it directly. There's no real game to research — you design a dramatic, specific match for the user, then WRITE it in the formula. Specificity is what sells it: pick a real goal mechanic for each scene, not "he scores."
  1. Design the match: the user's team ([TEAM]) vs [OPPONENT] in a huge night stadium. Decide the arc — the hero comes on with the team behind, equalizes, then scores a dramatic late winner. For each goal choose a concrete mechanic (a volley, a header off a cross, a turn-and-finish, a solo run, a free-kick) and a scoreline + minute. Use the two teams' kit colors throughout; opponent keeper/defenders by color only.
  2. Write exactly 3 scenes, 15s each, following the proven 3-act arc:
    • Scene 1 — "THE CALL": the hero comes on / kickoff for [TEAM], tension building, crowd roaring, a teammate or the bench urging them on.
    • Scene 2 — "THE EQUALIZER": the hero scores the equalizer vs [OPPONENT] with the chosen mechanic (real assist build-up, the strike, the keeper beaten) — e.g. 1-1.
    • Scene 3 — "THE WINNER": stoppage time, the hero scores the decisive goal, ending on the win + an on-screen final-score card.
  3. Scene-prompt formula (match this structure exactly — it's what makes it work):
    • Open with the style tag: 
      Japanese anime action style, cel-shaded, high contrast, [color grade e.g. cold desaturated → blazing gold], [intensity], [setting: packed night stadium, the minute + scoreline].
    • Beat-by-beat action naming the hero in CAPS with their kit colors, the exact goal mechanic, and anime camera/FX language: extreme close-up on the eyes, low heroic angle pushing up, slow dolly-in, anime smear frames, bullet-time on the strike, impact frame flashes pure white then SNAPS to full speed, net ripples, golden particle burst, motion-blur trail, frozen goalkeeper mid-dive.
    • Mood line: e.g. 
      brooding/determined → electric/triumphant → euphoric/explosive
      .
    • End with Japanese VO/subtitle lines, one per speaker, prefixed by the character's name, plus a commentator — short dialogue + the hero's inner monologue. Format: 
      VO/subtitle (JP): {NAME}「…」 / {NAME} (inner)「…」 / commentator「…」
    • Scene 3 also gets a final on-screen card: 
      Final on-screen card: {TEAM} {SCORE}.
    (Proven structural reference — the dramatic anime-match edit this format is modeled on; mirror its SHAPE exactly, swapping in YOUR hero name + YOUR team + the opponent: Scene 1 cold-graded close-up → strides on under floodlights, a teammate shouts, hero inner-monologue. Scene 2 a cross comes in → the HERO volleys it in, bullet-time + white impact flash, 1-1, keeper frozen. Scene 3 stoppage time, the HERO turn-and-spin finish past the defender, knee-slide, gold confetti, "[TEAM] 2-1" card. Each opens with the cel-shaded style tag and closes on JP dialogue + monologue + commentator. Reuse this shape; swap in your hero + teams + the goal mechanics you designed.)
这一步是创作者在Claude中完成的工作。你需直接执行。无需研究真实比赛——你要为用户量身设计一场具体且富有戏剧性的比赛，然后按照公式撰写提示语。细节是关键：为每个场景选择真实的进球机制，而非“他进球了”这种笼统描述。
  1. 设计比赛：用户支持的球队([支持球队])对阵[对手球队]，比赛在大型夜间体育场进行。设定剧情弧——主角登场时球队处于落后，随后扳平比分，最后打入戏剧性的绝杀球。为每个进球选择具体的进球机制（抽射、头球破门、转身射门、单刀赴会、任意球）及比分+时间节点。全程使用两队的球衣配色；仅通过颜色描述对手门将/后卫。
  2. 撰写恰好3幕场景，每幕15秒，遵循经过验证的三幕结构：
    • 场景1 — “登场召唤”：主角为[支持球队]登场/开球，紧张感拉满，观众欢呼，队友或教练席鼓励主角。
    • 场景2 — “扳平比分”：主角使用选定的进球机制攻破[对手球队]球门（包含真实的助攻配合、射门动作、门将扑救）——例如比分变为1-1。
    • 场景3 — “绝杀进球”：补时阶段，主角打入制胜球，结尾展示最终比分的屏幕卡片。
  3. 场景提示公式（严格遵循此结构——这是成功的关键）：
    • 开头添加风格标签：
      Japanese anime action style, cel-shaded, high contrast, [色彩风格例如冷色调低饱和→炽热金色], [强度], [场景：座无虚席的夜间体育场，时间节点+比分].
    • 逐帧动作描述，需提及大写姓名的主角及其球衣配色、具体的进球机制，以及动漫镜头/特效术语：眼部特写、低角度英雄镜头向上推进、慢镜头推近、动漫拖影帧、射门时的子弹时间、撞击帧闪白后瞬间恢复全速、球网晃动、金色粒子爆发、运动模糊轨迹、门将扑救瞬间定格.
    • 情绪描述：例如
      阴郁/坚定 → 激动/振奋 → 狂喜/炸裂
      。
    • 结尾添加日语配音/字幕，每位角色一句台词，加上解说员台词——简短对话+主角内心独白。格式： 
      VO/subtitle (JP): {NAME}「…」 / {NAME} (inner)「…」 / commentator「…」
    • 场景3需额外添加最终屏幕卡片：
      Final on-screen card: {TEAM} {SCORE}.
    (经过验证的结构参考——此格式基于戏剧性动漫比赛剪辑建模；严格模仿其结构，替换为你的主角姓名+支持球队+对手球队：场景1冷色调特写→主角在灯光下登场，队友呼喊，主角内心独白。场景2传中→主角抽射破门，子弹时间+白色撞击闪，比分1-1，门将定格。场景3补时阶段，主角转身摆脱后卫射门得分，滑跪庆祝，金色纸屑飘落，显示“[支持球队] 2-1”卡片。每幕开头添加赛璐珞风格标签，结尾添加日语对话+独白+解说员台词。复用此结构；替换主角+球队+你设计的进球机制。)

Stage 3 — Generate each scene (
generate_reference_video
, seedance)

阶段3 — 生成各场景视频（
generate_reference_video
，seedance）

One call per scene. Use the character sheet as reference and map the hero name to the image via the Seedance 
@Image1
token.
Call 
generate_reference_video
with:
  • provider
    : 
    seedance
     · 
    seedance_backend
    : 
    ark
  • reference_images
    : the hero sheet (plus any extra character sheets used in THAT scene) — e.g. 
    [sheets[HERO]]
  • aspect_ratio
    : 
    16:9
     · 
    resolution
    : 
    1080p
     · 
    duration
    : 
    15
     · 
    sound
    : 
    true
     (the JP dialogue + dramatic SFX are the point here — this format KEEPS generated voice/audio)
  • prompt
    : a name→image mapping line, then the scene prompt. Example: 
    {HERO} is @Image1. <full Scene 1 prompt from Stage 2>
    Reference the hero via its 
    @ImageN
    token where it first appears so Seedance binds the likeness.
Fire all three in parallel (
background: true
) and poll. Re-roll a scene if: the goal mechanic is wrong, the face drifts off the sheet, or the title/score card text garbles. If a scene trips 
OutputAudioSensitiveContentDetected
, re-roll with a new seed (or, as a last resort, 
sound: false
for that scene only and add the dialogue as an overlay).
每幕场景单独调用一次。使用角色表作为参考，并通过Seedance的
@Image1
标记将主角姓名与图像关联。
调用
generate_reference_video
时需设置：
  • provider
    ：
    seedance
     · 
    seedance_backend
    ：
    ark
  • reference_images
    ：主角的角色表（加上该场景中使用的其他角色表）——例如
    [sheets[HERO]]
  • aspect_ratio
    ：
    16:9
     · 
    resolution
    ：
    1080p
     · 
    duration
    ：
    15
     · 
    sound
    ：
    true
    （日语对话+戏剧性音效是核心——此格式保留生成的语音/音频）
  • prompt
    ：姓名→图像映射行，随后是场景提示语。示例： 
    {HERO} is @Image1. <完整的场景1提示语（来自阶段2）>
    在主角首次出现的位置通过
    @ImageN
    标记关联角色表，确保Seedance绑定形象相似度。
并行触发三个场景的生成（
background: true
）并轮询结果。若出现以下情况需重新生成场景：进球机制错误、面部形象偏离角色表、比分/标题卡片文字错乱。若场景触发
OutputAudioSensitiveContentDetected
，需使用新种子重新生成（或最后手段：仅对该场景设置
sound: false
，随后添加对话作为叠加层）。

Stage 4 — Stitch

阶段4 — 拼接成片

Concatenate Scene 1 → 2 → 3 in order into the final ~45s, 16:9 1080p cut (
edit_concat
, or ffmpeg concat of normalized clips). Keep each scene's generated audio. Optionally lay a subtle epic-anime music bed under it (post-only) if the user wants one. Deliver the stitched MP4 + the 3 scene clips.
按顺序将场景1→2→3拼接为最终的约45秒、16:9 1080p成片（使用
edit_concat
，或ffmpeg拼接标准化片段）。保留每个场景的生成音频。若用户要求，可在后期添加轻柔的史诗动漫背景音乐。交付拼接后的MP4文件及三个单独的场景片段。

Settings quick-reference

设置速查表

StepToolKey settings
Character sheet
generate_image_edit
nano-banana-pro
 (gpt-image-2 rejects real-person photos), ref = user's photo, hero in team kit, 
16:9
Design + promptsyou (acting as Claude)a specific dramatic match → 3×15s scenes in the formula above
Scene video
generate_reference_video
seedance
/
ark
, sheet as ref, name→
@ImageN
map, 
16:9
, 
1080p
, 
15s
, 
sound:true
Stitch
edit_concat
/ ffmpeg		scenes in order, keep audio, ~45s
Optional: 
seedance-anime
(style help for the prompt voice) and 
seedance-director
can assist with shot phrasing — but the formula above already reproduces the target look.
步骤工具关键设置
角色表
generate_image_edit
nano-banana-pro
（gpt-image-2拒绝处理真实人物照片），参考图=用户照片，主角身着支持球队球衣，
16:9
设计+提示语你（以Claude身份）具体的戏剧性比赛→3×15秒场景，遵循上述公式
场景视频
generate_reference_video
seedance
/
ark
，角色表作为参考，姓名→
@ImageN
映射，
16:9
，
1080p
，
15s
，
sound:true
拼接
edit_concat
/ ffmpeg		场景按顺序排列，保留音频，约45秒
可选：
seedance-anime
（为提示语风格提供帮助）和
seedance-director
可协助镜头措辞——但上述公式已能还原目标风格。

Failure modes

故障排查

SymptomFix
Face changes between scenesAlways pass the character sheet (not the raw photo) as the reference on every scene; re-roll drifters; map the hero to its 
@ImageN
.
Goal looks generic / weakYou skipped the design step — pick a specific mechanic (volley / header / turn-and-finish), a scoreline, kit colors, and write the strike beat-by-beat.
Hero unnamed / no Japanese dialogueThe formula is mandatory: name the hero in CAPS, end every scene with the 
VO/subtitle (JP): …
block.
Score / title card text garbledKeep card text short ("[TEAM] 2-1"); re-roll; or burn it as a clean overlay in post.
Audio sensitive-content trip (
OutputAudioSensitiveContentDetected
)		Re-roll seed; last resort 
sound:false
for that scene + overlay the JP lines.
Copyright/sensitive-content trip on the VIDEO (
OutputVideoSensitiveContentDetected
)		A new seed alone won't clear it — it's the content. Walkout / ceremony / broadcast-style scenes trip it most. De-brand the prompt: no named tournament ("World Cup" → "a huge night stadium"), no real club crests/sponsor logos, no on-screen scoreboard / lower-thirds / broadcast graphics, no captain's armband. Describe kit COLORS only, keep it pure on-pitch action (open-play goal scenes pass first try).
Transient 
invalid_input
/ "Unknown provider: seedance-assets" / 
skill_crashed
mid-job		Pika-side backend hiccup, not your input. Re-fire the same call with a new seed. If it ran past ~4 min before failing, the content already cleared the safety pass.
content_policy
/ 
image_generation_user_error
on the character sheet		gpt-image-2 (OpenAI) blocks anime-editing a real person's photo. Use 
nano-banana-pro
 for the sheet (the default); don't retry gpt-image-2 with the same photo.
症状修复方案
不同场景中面部形象不一致始终将角色表（而非原始照片）作为每个场景的参考图；重新生成形象偏差的场景；将主角与
@ImageN
关联。
进球效果笼统/平淡你跳过了设计步骤——选择具体的进球机制（抽射/头球/转身射门）、比分、球衣配色，并逐帧描述射门动作。
主角未命名/无日语对话必须遵循公式：主角姓名大写，每幕场景结尾添加
VO/subtitle (JP): …
模块。
比分/标题卡片文字错乱卡片文字保持简短（例如“[支持球队] 2-1”）；重新生成；或在后期添加清晰的叠加层。
音频触发敏感内容检测（
OutputAudioSensitiveContentDetected
）		使用新种子重新生成；最后手段：对该场景设置
sound: false
并添加日语台词叠加层。
视频触发版权/敏感内容检测（
OutputVideoSensitiveContentDetected
）		仅更换种子无法解决——问题出在内容本身。退场/仪式/转播风格场景最易触发。去品牌化提示语：不提及具体赛事名称（“世界杯”→“大型夜间体育场”），不使用真实俱乐部徽章/赞助商标志，不添加屏幕比分板/下方字幕/转播图形，不出现队长袖标。仅描述球衣颜色，专注于纯粹的场上动作（运动战进球场景通常能通过审核）。
临时出现
invalid_input
/ “Unknown provider: seedance-assets” / 
skill_crashed
Pika端后端故障，与你的输入无关。使用新种子重新触发相同调用。若故障发生在运行约4分钟后，说明内容已通过安全审核。
角色表生成触发
content_policy
/ 
image_generation_user_error
gpt-image-2（OpenAI）禁止对真实人物照片进行动漫化编辑。使用**
nano-banana-pro
**生成角色表（默认选项）；请勿使用同一张照片重试gpt-image-2。

Notes

注意事项

  • Pipeline: image-sheet → designed scene prompts → Seedance 15s scenes → stitch — built entirely on the Pika MCP, with the user as the hero (their photo + team + opponent).
  • Default output: 3 scenes × 15s = ~45s, 16:9, 1080p, anime cel-shaded, Japanese VO. Aspect/length configurable if the user asks (e.g. 9:16 for reels).
  • 流程：角色表→设计场景提示语→Seedance生成15秒场景视频→拼接成片——完全基于Pika MCP打造，用户为主角（基于其照片+支持球队+对手球队）。
  • 默认输出：3幕×15秒=约45秒，16:9，1080p，赛璐珞风格动漫，日语配音。若用户要求，可调整宽高比/时长（例如9:16适配短视频平台）。