flux-3-prompt-doctor

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

FLUX 3 Prompt Doctor

FLUX 3 提示词诊断工具

Resolve the decisions that change routing, payload, or production method before a brief becomes a prompt. Ask only blocking questions; use documented defaults or label assumptions for everything else. Preserve the user's product names, exact copy, source roles, and hard constraints verbatim. This skill does not write the final prompt or call the API.

在需求简报转化为提示词之前，解决会改变路由、负载或生成方式的决策问题。仅提出阻碍性问题；其他所有事项使用已记录的默认值或标记假设。严格保留用户的产品名称、精确文案、来源角色和硬性约束。本技能不撰写最终提示词或调用API。

Route by what must survive

按必须保留的内容路由

Every request names its

mode

and carries the matching media field:

Requirement	Route
Generate the whole clip from words	`mode: "t2v"` , no media
An image must appear on screen exactly as shot	`mode: "i2v"` , `keyframes`
Bridge an exact opening and closing frame	`mode: "i2v"` , two keyframes
Pass through visual waypoints	`mode: "i2v"` , keyframes as a storyboard
Continue from an existing ending	`mode: "v2v"` , `start_video`
Render an approved draft without replanning	`mode: "draft_enhance"` , `draft_cache`

Two questions separate the image routes: must these exact pixels be on screen (

keyframes

)? Can the source simply be described (then attach nothing)? There is no field that carries a subject's identity without putting the source on screen; a brief that needs one either opens each shot from a keyframe containing the subject, or is a

REVISE

每个请求都会指定其

mode

并携带匹配的媒体字段：

需求	路由
从文字生成完整片段	`mode: "t2v"` ，无媒体
图像必须完全按拍摄原样出现在屏幕上	`mode: "i2v"` ， `keyframes`
衔接精确的开头和结尾帧	`mode: "i2v"` ，两个关键帧
传递视觉途经点	`mode: "i2v"` ，关键帧作为分镜脚本
从现有结尾继续生成	`mode: "v2v"` ， `start_video`
渲染已获批的草稿，无需重新规划	`mode: "draft_enhance"` ， `draft_cache`

区分图像路由的两个问题：这些精确像素必须出现在屏幕上吗（

keyframes

）？是否只需描述来源即可（无需附加任何内容）？没有字段可以在不将来源显示在屏幕上的情况下传递主体身份；需要主体身份的简报要么从包含该主体的关键帧开始每个镜头，要么属于

REVISE

类型。

Feasibility

可行性

Action budget: one subject action and one camera move per short clip. Revise briefs demanding many sequential actions, several locations, exact mechanisms, or multiple full dialogue lines.

Shot structure: state one continuous unbroken take, or an explicit sequence:

text

SHOT ONE: wide aerial of a desert highway at dawn, a single red car speeding through.
HARD CUT. SHOT TWO: interior close-up, the driver's hands drumming the wheel to the radio.
HARD CUT. SHOT THREE: from the roadside, the car shrinking into the heat haze.
Warm engine hum under one continuous music bed across all three shots.

Consecutive shots must contrast hard (scale, location, color) or the cut blends into a continuous take; each shot needs its own beat; one music bed can run across cuts.

Contradictions to catch: locked-off camera plus tracking; extreme close-up plus establishing view; exact frame preservation plus major geometric change; one continuous shot plus hard cuts; production-critical generated typography with no post fallback; guaranteed speaker identity across separate generations.
Reserve for deterministic post when exactness is a success condition: typography, subtitles, logos; frame-accurate sync; final mixing; precise mechanisms; cross-generation speaker identity. Generation creates footage and causal intent, not a compositor or final mix.

动作预算：每个短片段包含一个主体动作和一个镜头移动。对于要求多个连续动作、多个场景、精确机械细节或多段完整对话的简报，需进行修订。

镜头结构：说明是一个连续不间断的镜头，还是明确的镜头序列：

text

SHOT ONE: wide aerial of a desert highway at dawn, a single red car speeding through.
HARD CUT. SHOT TWO: interior close-up, the driver's hands drumming the wheel to the radio.
HARD CUT. SHOT THREE: from the roadside, the car shrinking into the heat haze.
Warm engine hum under one continuous music bed across all three shots.

连续镜头必须形成强烈对比（规模、场景、色彩），否则剪辑会融合成一个连续镜头；每个镜头需要有自己的节奏；单个背景音乐可以贯穿多个剪辑。

需排查的矛盾点：固定镜头加跟踪移动；极端特写加全景镜头；精确帧保留加重大几何变化；单个连续镜头加硬切；生产关键的生成式排版无后期备选方案；跨多次生成保证说话者身份一致。
当精确性是成功条件时，预留用于确定性后期制作：排版、字幕、标志；帧级精确同步；最终混音；精确机械细节；跨生成的说话者身份一致性。生成过程负责创建素材和因果意图，而非合成或最终混音。

Verdict

结论

Return exactly one state, with a reason, next action, and a compact handoff (templates/brief.md when it should be reusable):

READY: route, assumptions, handoff. Recommend a draft first when the concept is unproven.
NEEDS INFO: only the blocking questions.
REVISE: name the conflict and the minimum repair.

Non-blocking warnings go under Production risks, not a fourth state. Field names and limits belong to the API reference; flag intent conflicts and leave schema validation to

flux-3-generate

返回以下精确状态之一，附带原因、下一步操作和简洁的交接内容（当简报可复用时使用templates/brief.md模板）：

READY：路由信息、假设内容、交接内容。当概念未经验证时，建议先生成草稿。
NEEDS INFO：仅列出阻碍性问题。
REVISE：指出冲突点和最小修复方案。

非阻碍性警告放在生产风险部分，而非第四种状态。字段名称和限制请参考API参考文档；只需标记意图冲突，将 schema 验证交给

flux-3-generate

处理。