higgsfield-youtube-thumbnail

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Higgsfield YouTube Thumbnail

Higgsfield YouTube缩略图制作

Create a clean thumbnail concept, generate each variant through the

higgsfield

CLI, inspect it, and make only requested surgical edits.

创建简洁的缩略图概念，通过

higgsfield

CLI生成每个变体，进行检查并仅根据请求进行精准微调。

Bootstrap

准备工作

Before any generation:

higgsfield

is missing, install it:

bash

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

higgsfield account status

reports

Session expired

Not authenticated

, ask the user to run

higgsfield auth login

, then wait.

Confirm the locked model contracts when the catalog may have changed:

bash

higgsfield model get nano_banana_pro --json
higgsfield model get gpt_image_2 --json
higgsfield model get seedream_v5_pro --json

在开始生成前：

如果未安装

higgsfield

，请执行安装：

bash

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

如果

higgsfield account status

显示

Session expired

或

Not authenticated

，请让用户运行

higgsfield auth login

，然后等待完成。

当模型目录可能发生变化时，确认锁定的模型合约：

bash

higgsfield model get nano_banana_pro --json
higgsfield model get gpt_image_2 --json
higgsfield model get seedream_v5_pro --json

UX rules

用户体验规则

Match the user's language. Keep CLI/model mechanics out of normal chat.
Do not ask for facts already present in the brief. Ask one compact question only when a missing choice changes the result.
Never invent claims, outcomes, products, people, screenshots, or statistics that are not true of the video.
Do not print raw JSON or job IDs to the user. Deliver the image URL and a short variant label.
A style-reference thumbnail is for visual analysis only. Never pass it with
```
--image
```
; copying its identity or exact composition is forbidden.
Do not use
```
--count
```
. Every concept, emotion, or camera take gets its own prompt and generation call.
```
use_unlim
```
is not a current CLI parameter. Never add
```
--use-unlim
```
; if the user explicitly asks to use an unlimited allowance, explain that this workflow must run on credits in CLI or through a surface that supports that allowance.

使用用户的语言进行沟通。在常规对话中不要提及CLI/模型的技术细节。
不要询问 brief 中已包含的信息。仅当缺少的选项会影响结果时，提出一个简洁的问题。
绝不能编造关于视频的不实声明、成果、产品、人物、截图或统计数据。
不要向用户展示原始JSON或任务ID。仅提供图片URL和简短的变体标签。
风格参考缩略图仅用于视觉分析。绝不能通过
```
--image
```
参数传入；禁止复制其人物身份或精确构图。
不要使用
```
--count
```
参数。每个概念、情绪或镜头都需要单独的提示词和生成调用。
```
use_unlim
```
并非当前CLI的可用参数。绝不能添加
```
--use-unlim
```
；如果用户明确要求使用不限量额度，请说明此工作流必须使用CLI中的 credits，或通过支持该额度的界面运行。

Intake gates

信息收集要点

Collect only what the brief does not answer:

The video's topic/title and the truthful promise the thumbnail may imply.
Exact scene requirements, if any.
Who appears: 0–3 people. If a concept needs a person and no face photo was provided, ask whether to use the user, another provided person, or a generic generated character. Never choose silently.
Optional style-reference thumbnail. Analyze it with host vision for energy, framing, split layout, palette, and emotion; do not send it to Higgsfield.
Optional logo and whether it stays flat or becomes a 3D object.
Optional headline, 2–4 words. Default delivery is a clean image with no text. Use a deterministic overlay when the user requests an overlay; bake text into the generated image only when explicitly requested.
Ratio:
```
16:9
```
for YouTube by default,
```
9:16
```
for Shorts, or
```
4:5
```
for Instagram.
One final concept or a variant set. If unspecified and alternatives would materially help, offer a set of about four. Hard cap: 16 total generations.

If the user gives an emotion count without names, use this ladder: shock, hype, rage, awe, laugh, fear, smug, charisma, confusion, determination, disgust.

仅收集brief中未提及的信息：

视频的主题/标题，以及缩略图可传达的真实承诺。
具体的场景要求（如有）。
出现的人物：0–3人。如果概念需要人物但未提供面部照片，请询问是否使用用户本人、其他提供的人物，或通用生成角色。切勿自行决定。
可选的风格参考缩略图。通过视觉分析其活力、构图、分屏布局、配色和情绪；不要将其发送给Higgsfield。
可选的logo，以及是否保持平面样式或转为3D对象。
可选的标题，2–4个词。默认交付无文字的干净图片。当用户要求叠加文字时，使用确定性的叠加方式；仅在明确要求时，才将文字嵌入生成的图片中。
比例：默认YouTube使用
```
16:9
```
，Shorts使用
```
9:16
```
，Instagram使用
```
4:5
```
。
单一最终概念或一组变体。如果未指定且备选方案能提供实质性帮助，可提供约4个变体的集合。上限：总共16次生成。

如果用户仅给出情绪数量而未指定具体情绪，请使用以下层级：震惊、兴奋、愤怒、敬畏、大笑、恐惧、得意、魅力、困惑、坚定、厌恶。

Concept gate

概念审核

Read

references/thumbnail-frameworks.md

. Brainstorm at least five truthful concepts internally, across multiple frameworks, then select the strongest information gap with one focal subject and minimal clutter. Combine frameworks only when the result still reads in under one second at roughly 120px wide.

When a reference thumbnail exists, extract this structure before prompting:

text

brief, generic subject pose/action, elements, location, composition, background,
split (true/false), split_count, person_count, emotion, emotion_detail

The reference supplies art direction, never a specific identity. User instructions override it field by field.

阅读

references/thumbnail-frameworks.md

。在内部构思至少5个符合真实原则的概念，涵盖多种框架，然后选择最具吸引力的信息差概念，包含一个核心主体且尽量简洁。仅当组合后的框架在约120px宽度下仍能在1秒内被理解时，才进行框架组合。

当存在参考缩略图时，在编写提示词前提取以下结构：

text

brief, generic subject pose/action, elements, location, composition, background,
split (true/false), split_count, person_count, emotion, emotion_detail

参考素材仅提供艺术指导，而非特定人物身份。用户的指令会逐字段覆盖参考素材的设置。

Reference order

参考素材顺序

Pass face photos first in character order, then the logo. Repeat

--image

for every reference. When two or more references are attached, the prompt's first line must be a manifest such as:

text

IMAGE REFERENCES: image 1 = CHARACTER 1 face reference; image 2 = brand logo.

Local paths are auto-uploaded. Previous completed job IDs also work as

--image

inputs.

按人物顺序优先传入面部照片，然后是logo。每个参考素材都需重复使用

--image

参数。当附加两个或更多参考素材时，提示词的第一行必须是清单，例如：

text

IMAGE REFERENCES: image 1 = CHARACTER 1 face reference; image 2 = brand logo.

本地路径会自动上传。之前完成的任务ID也可作为

--image

输入。

Prompt contract

提示词规范

Assemble every main-render prompt in this order:

Frame:

Bold, punchy YouTube-thumbnail composite — poster-grade, photoreal and high-impact, NOT a muted cinematic movie still, <ratio>, single unified frame — no split-screen, no diagonal divide, everything blends smoothly and organically across the same continuous shot.

For

9:16

, add

faces in the upper two-thirds

. A requested graphical representation replaces photoreal language with a clean diagram/graphic brief.

Scene brief: depict the user's exact content.

Text: default

No text, no readable UI labels, no watermark.

For explicit baked headline:

TEXT: bold thumbnail headline text baked into the image, reading exactly "<TEXT>" — massive, ultra-legible sans-serif with a clean outline/glow treatment, placed where it never covers the subject's face. No other text, no watermark.

Subjects: large, foreground-dominant, chest-up or medium-close, filling about 40–60% of the frame. End with
```
All faces crisply sharp as the anchors of the shot.
```
Key elements: only signature props/effects that explain the information gap.
Logo: preserve exact shapes, colors, proportions, and letterforms; keep it away from faces.
Location: place, time, weather, and atmosphere when relevant.
Composition: one power-third hero, clear scale hierarchy, depth, and strong subject/background separation.
Background: vivid high-contrast color field or environment, soft vignette and edge falloff; do not divide it unless a split layout was explicitly requested.

Lighting on people:

signature YouTube thumbnail lighting rig — strong key light sculpting the face, soft dreamy fill lifting shadows, and defined back light plus hair light tracing a clean bright rim around hair, shoulders and silhouette.

Only the rim may use a colored accent.

Grade: vivid, bright, glossy, poster-punchy, deep blacks, crisp highlights, rich saturated colors, cohesive as one image. Restrain it only for an explicit calm/premium/muted brief.

For each photo-referenced person, include:

text

CHARACTER N: the person from attached face reference #K — IDENTITY LOCK: reproduce
this exact person with a photographic identity match — same bone structure, eye shape,
nose, lips, jawline, skin tone, hairline and hair texture. Do not beautify, average,
or restyle the face. Expression: <emotion phrase>.

主渲染提示词需按以下顺序组装：

框架：

Bold, punchy YouTube-thumbnail composite — poster-grade, photoreal and high-impact, NOT a muted cinematic movie still, <ratio>, single unified frame — no split-screen, no diagonal divide, everything blends smoothly and organically across the same continuous shot.

对于

9:16

比例，添加

faces in the upper two-thirds

。如果要求图形化呈现，则将写实风格的描述替换为简洁的图表/图形说明。

场景说明： 准确呈现用户指定的内容。

文字： 默认

No text, no readable UI labels, no watermark.

如果明确要求嵌入标题：

TEXT: bold thumbnail headline text baked into the image, reading exactly "<TEXT>" — massive, ultra-legible sans-serif with a clean outline/glow treatment, placed where it never covers the subject's face. No other text, no watermark.

主体： 大尺寸、前景主导、胸部以上或中近景，占据画面约40–60%的比例。结尾添加
```
All faces crisply sharp as the anchors of the shot.
```
关键元素： 仅包含能解释信息差的标志性道具/效果。
Logo： 保留精确的形状、颜色、比例和字体；远离人物面部。
场景： 相关的地点、时间、天气和氛围。
构图： 采用三分法突出主体，清晰的比例层级、深度，以及主体与背景的明确分离。
背景： 鲜明的高对比度色块或环境，柔和的暗角和边缘渐变；除非明确要求分屏布局，否则不要分割背景。

人物灯光：

signature YouTube thumbnail lighting rig — strong key light sculpting the face, soft dreamy fill lifting shadows, and defined back light plus hair light tracing a clean bright rim around hair, shoulders and silhouette.

仅轮廓光可使用彩色点缀。

调色： 鲜艳、明亮、有光泽、海报级冲击力，深邃的黑色、清晰的高光、浓郁饱和的色彩，整体风格统一。仅当明确要求平静/高端/柔和风格时，才调整调色。

对于每个带照片参考的人物，需包含：

text

CHARACTER N: the person from attached face reference #K — IDENTITY LOCK: reproduce
this exact person with a photographic identity match — same bone structure, eye shape,
nose, lips, jawline, skin tone, hairline and hair texture. Do not beautify, average,
or restyle the face. Expression: <emotion phrase>.

Split layouts

分屏布局

Use a split only when the user asks for

split

before/after

versus

side by side

, or the analyzed reference is split. A topical phrase such as

X vs Y

does not itself require a split. Replace the normal frame block with a clear halves/panels contract and keep all labels out unless short, truthful baked UI was explicitly requested.

仅当用户要求

split

、

before/after

、

versus

、

side by side

，或分析后的参考素材为分屏时，才使用分屏布局。诸如

X vs Y

的主题表述本身并不要求分屏。将常规框架部分替换为清晰的分屏/面板规范，除非明确要求简短的真实嵌入UI，否则不要添加任何标签。

Optional 3D logo

可选3D logo生成

First create a 1:1 4K logo render, then use its completed job ID as the last

--image

on every thumbnail call:

bash

higgsfield generate create gpt_image_2 \
  --prompt "Transform the attached 2D logo into a premium 3D logo render: extrude the exact logo shapes into glossy dimensional volumes; preserve every letterform, proportion and brand color; soft studio reflections, subtle bevels, crisp edges, clean dark neutral background, soft contact shadow, centered, generous margins, no extra text, no watermark." \
  --image ./logo.png \
  --aspect_ratio 1:1 \
  --quality high \
  --resolution 4k \
  --wait --json

首先生成1:1比例的4K logo渲染图，然后将其完成的任务ID作为最后一个

--image

参数传入每个缩略图生成调用：

bash

higgsfield generate create gpt_image_2 \
  --prompt "Transform the attached 2D logo into a premium 3D logo render: extrude the exact logo shapes into glossy dimensional volumes; preserve every letterform, proportion and brand color; soft studio reflections, subtle bevels, crisp edges, clean dark neutral background, soft contact shadow, centered, generous margins, no extra text, no watermark." \
  --image ./logo.png \
  --aspect_ratio 1:1 \
  --quality high \
  --resolution 4k \
  --wait --json

Main render

主图渲染

Use Nano Banana Pro at explicit 4K. Write the final prompt to a temporary text file and pipe it on stdin so punctuation and multiline blocks are preserved safely:

bash

higgsfield generate create nano_banana_pro \
  --aspect_ratio 16:9 \
  --resolution 4k \
  --image ./face-1.png \
  --image ./logo.png \
  --wait --json < thumbnail-prompt.txt

Omit all

--image

flags when there are no references. For a variant set, make one call per distinct prompt. Keep the same references and settings; vary only the selected concept, expression, or camera-take line.

The completed JSON result contains

id

and

result_url

. Preserve both privately: the URL is delivered; the ID is the source for later edits.

使用Nano Banana Pro生成明确的4K分辨率图片。将最终提示词写入临时文本文件，并通过标准输入传入，以确保标点符号和多行内容被安全保留：

bash

higgsfield generate create nano_banana_pro \
  --aspect_ratio 16:9 \
  --resolution 4k \
  --image ./face-1.png \
  --image ./logo.png \
  --wait --json < thumbnail-prompt.txt

当没有参考素材时，省略所有

--image

参数。对于变体集合，每个不同的提示词对应一次调用。保持相同的参考素材和设置；仅改变所选的概念、表情或镜头描述。

完成后的JSON结果包含

id

和

result_url

。需私下保存两者：URL用于交付；ID用于后续编辑。

Post-render gate

渲染后审核

Inspect every result with host vision when available:

Referenced identities visibly match.
No stray text or watermark exists unless baked text was ordered.
Explicit baked text matches character-for-character.
The face/emotion and hero element remain readable at about 120px wide.
The concept truthfully matches the video promise.

On a hard failure, retry the same prompt at most twice. If visual inspection is unavailable, do not claim it passed; deliver the result for user review. Present every passing variant and let the user pick before making optional tweaks.

如果有视觉检查能力，需检查每个结果：

参考人物的身份是否清晰匹配。
除非要求嵌入文字，否则无多余文字或水印。
明确要求嵌入的文字需完全匹配。
在约120px宽度下，人物面部/情绪和核心元素仍清晰可辨。
概念与视频承诺真实相符。

如果出现严重失败，最多重试相同提示词两次。如果无法进行视觉检查，不要声称结果通过审核；将结果交付给用户进行审核。展示所有通过审核的变体，让用户选择后再进行可选的微调。

Surgical tweaks

精准微调

Use the picked completed job ID as the only image input. Keep the edit prompt narrowly scoped and state that every other pixel-level property remains unchanged.

bash

higgsfield generate create seedream_v5_pro \
  --prompt "Change ONLY the person's facial expression to: <phrase>. Keep identity, face structure, hair, pose, body, clothing, logo, background, lighting and composition EXACTLY unchanged, pixel-faithful. Keep the YouTube thumbnail lighting rig intact." \
  --image <picked_job_id> \
  --aspect_ratio 16:9 \
  --resolution 2k \
  --wait --json

seedream_v5_pro

is absent or rejects the submit, retry once with

seedream_v4_5 --quality high

. For a

4:5

main render, Seedream has no

4:5

; ask before changing the edit to

3:4

, and disclose the crop/ratio change. Each accepted edit becomes the source ID for the next tweak.

CLI compatibility: versions through

1.1.20

can mislabel a

nano_banana_pro

job reference as

nano_banana_pro_job

. If the edit is rejected with a

medias.0...data.type

error, download the picked

result_url

to a local image and retry the same edit with

--image ./picked-thumbnail.png

. A local path is auto-uploaded as

media_input

; do not retry the invalid job-id payload.

Allowed tweak scopes: expression only, background replacement only, background recolor only, or rim-light recolor only. Never silently regenerate the full composition for a surgical request.

将用户选择的完成任务ID作为唯一的图片输入。微调提示词需范围狭窄，并说明其他所有像素级属性保持不变。

bash

higgsfield generate create seedream_v5_pro \
  --prompt "Change ONLY the person's facial expression to: <phrase>. Keep identity, face structure, hair, pose, body, clothing, logo, background, lighting and composition EXACTLY unchanged, pixel-faithful. Keep the YouTube thumbnail lighting rig intact." \
  --image <picked_job_id> \
  --aspect_ratio 16:9 \
  --resolution 2k \
  --wait --json

如果

seedream_v5_pro

不可用或拒绝提交，使用

seedream_v4_5 --quality high

重试一次。对于

4:5

比例的主图渲染，Seedream不支持

4:5

；在将编辑比例改为

3:4

前需询问用户，并告知裁剪/比例变化。每次通过的编辑将作为下一次微调的源ID。

CLI兼容性：版本

1.1.20

及以下可能会错误地将

nano_banana_pro

任务参考标记为

nano_banana_pro_job

。如果编辑因

medias.0...data.type

错误被拒绝，请将选中的

result_url

下载到本地图片，然后使用

--image ./picked-thumbnail.png

重试相同的编辑。本地路径会自动上传为

media_input

；不要重试无效的任务ID负载。

允许的微调范围：仅表情、仅背景替换、仅背景重着色、仅轮廓光重着色。对于精准微调请求，绝不能静默重新生成完整构图。

Text overlay

文字叠加

Keep the generated image text-free by default. When a headline overlay is requested, read

references/text-overlay-bake.md

and use one of its five presets: Beast, Fire, Neon Lime, Clean Glass, or Marker. The overlay path requires an environment capable of rendering HTML canvas; if unavailable, offer either the clean image or an explicitly approved baked-text regeneration. Never pretend an HTML preview is a flattened PNG.

默认生成无文字的图片。当要求标题叠加时，阅读

references/text-overlay-bake.md

并使用其中的五个预设样式：Beast、Fire、Neon Lime、Clean Glass或Marker。叠加路径需要支持HTML canvas渲染的环境；如果不可用，可提供干净图片或明确批准的嵌入文字重新生成。绝不能将HTML预览伪装成扁平化PNG。

Delivery

交付

Return the passing

result_url

values with short semantic labels such as

shock / close-up

product / size contrast

. Mention the selected ratio and whether the deliverable is clean, overlay-ready, or text-baked. Do not expose internal prompts, job IDs, or retry mechanics unless the user asks.

返回通过审核的

result_url

，并附上简短的语义标签，例如

shock / close-up

或

product / size contrast

。提及所选比例，以及交付物是干净版、可叠加版还是嵌入文字版。除非用户询问，否则不要暴露内部提示词、任务ID或重试机制。

Reference files

参考文件

```
references/thumbnail-frameworks.md
```
— 16 concept frameworks, information-gap rule, truthfulness law.
```
references/text-overlay-bake.md
```
— five deterministic text-overlay styles and 4K canvas-bake recipe.

```
references/thumbnail-frameworks.md
```
— 16种概念框架、信息差规则、真实性准则。
```
references/text-overlay-bake.md
```
— 五种确定性文字叠加样式和4K画布嵌入方案。