flux-2-klein

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

🎨 Flux 2 Klein — Pro Pack on RunComfy

🎨 Flux 2 Klein — RunComfy专业套装

runcomfy.com · 9B model · 4B model · GitHub

Black Forest Labs' Flux 2 Klein (the distilled, low-latency variant of Flux 2) hosted on the RunComfy Model API — no API key, async REST.

bash

npx skills add agentspace-so/runcomfy-skills --skill flux-2-klein -g

runcomfy.com · 9B模型 · 4B模型 · GitHub

Black Forest Labs推出的Flux 2 Klein（Flux 2的精简低延迟变体）托管在RunComfy Model API上——无需API密钥，支持异步REST调用。

bash

npx skills add agentspace-so/runcomfy-skills --skill flux-2-klein -g

When to pick this model (vs siblings)

何时选择该模型（对比同类模型）

Flux 2 Klein's distinct strength is latency-first creative iteration: sub-second feedback enables live art-direction sessions and rapid product visualization that batch-style models can't sustain. Pick it when iteration speed matters more than ceiling resolution.

You want	Use
Real-time / live art-direction sessions	Flux 2 Klein 4B ✓
Fast iteration with strong detail at the end	Flux 2 Klein 9B ✓
Multi-reference brand styling with consistent looks	Flux 2 Klein ✓
2K–4K hero images, max resolution	Seedream 5
Maximum prompt adherence + extreme detail	Flux 2 Pro
Embedded text, logos, multilingual signage	GPT Image 2
Hyperrealistic portrait	Nano Banana Pro

If the user said "Flux 2 Klein" / "BFL Klein" / "flux klein" explicitly, route here regardless. If they said "Flux 2" generically, ask whether they want Klein (fast) or Pro (max quality) before defaulting.

Flux 2 Klein的核心优势是以延迟优先的创意迭代：亚秒级反馈支持实时艺术指导会话和快速产品可视化，这是批量式模型无法实现的。当迭代速度比最高分辨率更重要时，选择它。

需求场景	推荐模型
实时/现场艺术指导会话	Flux 2 Klein 4B ✓
快速迭代且最终输出细节丰富	Flux 2 Klein 9B ✓
多参考品牌风格且视觉一致	Flux 2 Klein ✓
2K–4K主视觉图、最高分辨率	Seedream 5
最大程度遵循提示词+极致细节	Flux 2 Pro
嵌入文本、标识、多语言标牌	GPT Image 2
超写实肖像	Nano Banana Pro

如果用户明确提到“Flux 2 Klein” / “BFL Klein” / “flux klein”，无论其他情况都路由至此模型。如果用户笼统提到“Flux 2”，在默认选择前需询问他们想要Klein（高速）还是Pro（最高质量）。

Prerequisites

前置条件

RunComfy CLI —
```
npm i -g @runcomfy/cli
```
RunComfy account —
```
runcomfy login
```
opens a browser device-code flow.
CI / containers — set
```
RUNCOMFY_TOKEN=<token>
```
instead of
```
runcomfy login
```
.

RunComfy CLI — 执行
```
npm i -g @runcomfy/cli
```
安装
RunComfy账户 — 执行
```
runcomfy login
```
会打开浏览器设备码登录流程
CI/容器环境 — 设置环境变量
```
RUNCOMFY_TOKEN=<token>
```
替代
```
runcomfy login
```

Endpoints + input schema

端点与输入 schema

Two variants, same endpoint shape, same prompt grammar.

两个变体的端点结构和提示词语法一致。

blackforestlabs/flux-2-klein/9b/text-to-image

blackforestlabs/flux-2-klein/9b/text-to-image

The fidelity-first variant. Use for polish / final output.

Field	Type	Required	Default	Notes
`prompt`	string	yes	—	Up to ~512 tokens. Longer degrades.
`steps`	int	no	25	4–50. Step-distilled architecture — 4–8 enough for concepting; ~25 for polish; >25 buys little.
`width`	int	no	1024	512–1536 typical. Aspect ratio capped at 16:9, max ~2K total.
`height`	int	no	1024	Match `width` 's aspect intent.

以保真度优先的变体，用于精细化打磨/最终输出。

字段	类型	是否必填	默认值	说明
`prompt`	字符串	是	—	最多约512个token，过长会降低输出质量
`steps`	整数	否	25	取值范围4–50。步数精简架构：4–8步足够用于概念构思；约25步用于精细化打磨；超过25步提升有限
`width`	整数	否	1024	典型取值512–1536。宽高比上限为16:9，总像素约2K
`height`	整数	否	1024	需与 `width` 的宽高比意图匹配

blackforestlabs/flux-2-klein/4b/text-to-image

blackforestlabs/flux-2-klein/4b/text-to-image

The latency-first variant. Sub-second 4-step inference. Use for live iteration / concepting.

Same field set as 9B. Default

steps

is effectively 4 — the variant is built for that step count.

以延迟优先的变体，4步推理可实现亚秒级输出，用于实时迭代/概念构思。

字段集与9B变体一致，默认

steps

为4——该变体专为这个步数设计。

Reference images (both variants)

参考图像（两个变体均支持）

Up to 4 simultaneous reference images are supported on the same endpoint for style transfer / guided composition. The exact field name in the JSON body is documented on the model's API tab — pass it through the CLI verbatim. Reference-image use enables editing-style workflows without a separate

/edit

endpoint.

同一端点最多支持4张同时传入的参考图像，用于风格迁移/构图引导。JSON请求体中的具体字段名称可在模型API页面查看——直接通过CLI传入即可。参考图像功能支持编辑类工作流，无需单独调用

/edit

端点。

How to invoke

调用方式

Fast concepting (4B, sub-second):

bash

runcomfy run blackforestlabs/flux-2-klein/4b/text-to-image \
  --input '{"prompt": "<user prompt>"}' \
  --output-dir <absolute/path>

Polish / final (9B, ~25 steps):

bash

runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image \
  --input '{
    "prompt": "<user prompt>",
    "steps": 25,
    "width": 1024,
    "height": 1024
  }' \
  --output-dir <absolute/path>

Wide-format poster:

bash

runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image \
  --input '{"prompt": "<user prompt>", "width": 1536, "height": 864}' \
  --output-dir <absolute/path>

The CLI submits, polls every 2s until terminal, then downloads any

*.runcomfy.net

*.runcomfy.com

URL from the result into

--output-dir

. Stdout is the result JSON. Stderr is progress.

For pipe-friendly usage:

bash

runcomfy --output json run blackforestlabs/flux-2-klein/4b/text-to-image \
  --input '{"prompt":"..."}' --no-wait | jq -r .request_id

快速概念构思（4B，亚秒级）：

bash

runcomfy run blackforestlabs/flux-2-klein/4b/text-to-image \
  --input '{"prompt": "<用户提示词>"}' \
  --output-dir <绝对路径>

精细化打磨/最终输出（9B，约25步）：

bash

runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image \
  --input '{
    "prompt": "<用户提示词>",
    "steps": 25,
    "width": 1024,
    "height": 1024
  }' \
  --output-dir <绝对路径>

宽幅海报：

bash

runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image \
  --input '{"prompt": "<用户提示词>", "width": 1536, "height": 864}' \
  --output-dir <绝对路径>

CLI提交请求后，每2秒轮询一次直到任务完成，然后将结果中所有

*.runcomfy.net

*.runcomfy.com

的URL下载到

--output-dir

目录。标准输出为结果JSON，标准错误输出为进度信息。

管道友好型用法：

bash

runcomfy --output json run blackforestlabs/flux-2-klein/4b/text-to-image \
  --input '{"prompt":"..."}' --no-wait | jq -r .request_id

Prompting — what actually works

有效提示词技巧

These are model-specific patterns that empirically improve output quality.

Subject-first declarative grammar. The structure Flux 2 Klein was trained on is "Subject + action + scene + style + lighting + camera + quality". Front-load the subject; trail with directives. Example:

"A vibrant hummingbird mid-flight sipping nectar from a bright pink hibiscus, iridescent feathers in morning sun, soft bokeh tropical garden, macro photography, razor-sharp detail, cinematic lighting"

Specificity wins over flowery language. "4k product photo, softbox lighting, reflective table, 35mm, f/2.8" guides predictably. "A really pretty product image" doesn't.

Step-count by phase.

Concepting: 4–8 steps on the 4B variant — sub-second feedback for live exploration.
Refinement: 8–15 steps still on 4B, locking in subject + framing.
Polish: ~25 steps on the 9B variant — texture, microdetail, fine typography.

Multi-reference alignment. When passing reference images, keep their aesthetics aligned. Mixing a watercolor + a photoreal + a 3D render in the same call confuses the editor. Pick one consistent visual register across all refs.

Conditional edits: state what stays, then what changes. "Same composition and lighting as reference, but change the background from beach to mountain studio." This pattern holds composition stable.

For text rendering (Klein has the 8B Qwen3 embedder, decent but not GPT Image 2 territory): add

"crisp typography, high-contrast label"

and bump steps to ~25 if the text comes out soft. For heavy in-image text or multilingual rendering, route to GPT Image 2 instead.

Anti-patterns:

Don't conflict adjectives. "minimalist + ornate" cancels.
Don't exceed ~512 tokens. The model degrades, doesn't truncate gracefully.
Don't ask for 4K — the model's resolution ceiling is ~2K.
Don't ask for ultra-wide (>16:9) — the model crops.

以下是经实践验证能提升输出质量的模型专属提示词模式。

主语优先的声明式语法。Flux 2 Klein的训练数据结构为*“主体 + 动作 + 场景 + 风格 + 光线 + 镜头 + 画质”*。将主体放在最前面，后面跟随指令。示例：

"一只色彩鲜艳的蜂鸟在飞行中吸食亮粉色木槿花的花蜜，早晨阳光下的虹彩羽毛，柔和散景的热带花园背景，微距摄影，极致锐利细节，电影级光线"

。

具体描述优于华丽辞藻。“4K产品照片，柔光箱照明，反光桌面，35mm镜头，f/2.8”能产生可预测的效果。“一张非常漂亮的产品图”则无法提供有效引导。

分阶段调整步数：

概念构思：使用4B变体，4–8步——亚秒级反馈支持实时探索
细化调整：仍使用4B变体，8–15步，锁定主体与构图
精细化打磨：使用9B变体，约25步——优化纹理、微细节、精细排版

多参考图像风格对齐。传入参考图像时，保持美学风格一致。在同一调用中混合水彩、写实、3D渲染风格会让模型产生混淆。所有参考图像需选择统一的视觉风格。

条件式编辑：先说明保留的内容，再说明修改的部分。例如：“与参考图像的构图和光线保持一致，但将背景从海滩改为山地工作室”。这种模式能稳定构图。

文本渲染技巧（Klein搭载8B Qwen3嵌入器，效果不错但不如GPT Image 2）：添加

"清晰排版，高对比度标签"

，如果文本显示模糊，将步数提升至约25步。如果需要大量嵌入文本或多语言渲染，建议转而使用GPT Image 2。

反模式：

避免使用矛盾形容词，比如“极简主义 + 华丽繁复”会相互抵消
提示词不要超过约512个token，模型性能会下降，且不会优雅截断
不要要求4K分辨率——模型的分辨率上限约为2K
不要要求超宽比例（>16:9）——模型会自动裁剪

Where it shines

适用场景

Use case	Why Flux 2 Klein
Live art-direction sessions	Sub-second feedback (4B) enables real-time iteration
Interactive product visualization	Fast UI previews and product comps without batch waits
Multi-reference brand styling	Strong style consistency across references for unified asset packs
Rapid concepting → polish workflow	4B for exploration, 9B for the final pass — same prompt grammar throughout
Consumer-GPU-friendly inference	4B variant runs on modest hardware; relevant for self-host comparisons but RunComfy-hosted is fine

使用场景	选择Flux 2 Klein的原因
实时艺术指导会话	亚秒级反馈（4B变体）支持实时迭代
交互式产品可视化	快速生成UI预览和产品效果图，无需等待批量处理
多参考品牌风格设计	跨参考图像的风格一致性强，适合生成统一的资产包
快速构思→精细化打磨工作流	4B变体用于探索，9B变体用于最终输出——全程使用相同的提示词语法
消费级GPU友好型推理	4B变体可在普通硬件上运行；虽然RunComfy托管版本已足够，但这一点在自托管对比中很重要

Sample prompts (verified to produce strong results)

验证有效的示例提示词

From the model page (BFL example):

A vibrant hummingbird mid-flight sipping nectar from a bright pink hibiscus
flower, iridescent emerald and sapphire feathers catching the morning sun,
soft bokeh tropical garden background, macro photography, razor-sharp
detail, cinematic lighting

Product-photo pattern:

A matte ceramic mug on a reclaimed-wood table, soft northern window light
from the left, shallow depth of field, 50mm prime, f/2.0, neutral
background, e-commerce ready, 4K product photography

Brand-consistent pair (multi-ref):

Same composition and lighting as the reference image, but the bottle
label is now blue with white sans-serif typography reading "AURA";
keep the bottle silhouette, table, and shadow exactly as in the reference

模型页面示例（BFL官方示例）：

一只色彩鲜艳的蜂鸟在飞行中吸食亮粉色木槿花的花蜜，虹彩般的祖母绿和蓝宝石羽毛在早晨阳光下熠熠生辉，柔和散景的热带花园背景，微距摄影，极致锐利细节，电影级光线

产品照片模式：

哑光陶瓷马克杯放在再生木桌面上，左侧柔和的北向窗户光线，浅景深，50mm定焦镜头，f/2.0，中性背景，适合电商平台，4K产品摄影

品牌风格一致的成对图像（多参考）：

与参考图像的构图和光线保持一致，但瓶身标签改为蓝色配白色无衬线字体，文字为“AURA”；保持瓶身轮廓、桌面和阴影与参考图像完全一致

Limitations

局限性

Resolution ceiling ~2K — for higher native res, route to Seedream 5.
Aspect ratio cap 16:9 — extreme wide/tall ratios get cropped.
Prompt cap ~512 tokens — longer degrades quality; doesn't truncate gracefully.
Reference image cap 4 — more than 4 increases latency and dilutes guidance.
Text rendering — the 8B Qwen3 embedder helps but GPT Image 2 still wins for embedded text precision.

分辨率上限约2K——如需更高原生分辨率，建议使用Seedream 5
宽高比上限16:9——极端宽/高比例会被裁剪
提示词上限约512个token——过长会降低输出质量，且不会优雅截断
参考图像上限4张——超过4张会增加延迟并削弱引导效果
文本渲染——8B Qwen3嵌入器有一定效果，但GPT Image 2在嵌入文本精度上仍更优

Exit codes

退出码

The

runcomfy

CLI uses sysexits-style codes:

code	meaning
0	success
64	bad CLI args
65	bad input JSON / schema mismatch (e.g. `width: 4096` would 422)
69	upstream 5xx
75	retryable: timeout / 429
77	not signed in or token rejected

Full reference: docs.runcomfy.com/cli/troubleshooting.

runcomfy

CLI使用sysexits风格的退出码：

代码	含义
0	成功
64	CLI参数错误
65	输入JSON错误/schema不匹配（例如 `width: 4096` 会返回422）
69	上游服务5xx错误
75	可重试：超时/429限流
77	未登录或令牌被拒绝

完整参考：docs.runcomfy.com/cli/troubleshooting。

How it works

工作原理

The skill invokes

runcomfy run blackforestlabs/flux-2-klein/<variant>/text-to-image

with a JSON body matching the schema.

The CLI POSTs to

https://model-api.runcomfy.net/v1/models/blackforestlabs/flux-2-klein/<variant>/text-to-image

with the user's bearer token.

The Model API returns a
```
request_id
```
; the CLI polls
```
GET .../requests/<id>/status
```
every 2 seconds.
On terminal status, the CLI fetches
```
GET .../requests/<id>/result
```
and downloads any URL whose host ends with
```
.runcomfy.net
```
or
```
.runcomfy.com
```
into
```
--output-dir
```
. Other URLs are listed but not fetched.
```
Ctrl-C
```
while polling sends
```
POST .../requests/<id>/cancel
```
so you don't get billed for GPU you stopped.

技能调用

runcomfy run blackforestlabs/flux-2-klein/<variant>/text-to-image

，传入符合schema的JSON请求体

CLI携带用户的Bearer令牌向

https://model-api.runcomfy.net/v1/models/blackforestlabs/flux-2-klein/<variant>/text-to-image

发送POST请求

Model API返回
```
request_id
```
；CLI每2秒轮询一次
```
GET .../requests/<id>/status
```
任务完成后，CLI获取
```
GET .../requests/<id>/result
```
，并将所有主机后缀为
```
.runcomfy.net
```
或
```
.runcomfy.com
```
的URL下载到
```
--output-dir
```
目录。其他URL仅列出但不下载
轮询时按
```
Ctrl-C
```
会发送
```
POST .../requests/<id>/cancel
```
请求，避免为已停止的GPU使用付费

What this skill is not

本技能不包含的内容

Not a self-hosted Flux runner. Not a capability grant — depends on a working RunComfy account. Not multi-tenant.

不是自托管Flux运行器。不提供独立能力——依赖可用的RunComfy账户。不支持多租户。

Security & Privacy

安全与隐私

Token storage:
```
runcomfy login
```
writes the API token to
```
~/.config/runcomfy/token.json
```
with mode 0600 (owner-only read/write). Set
```
RUNCOMFY_TOKEN
```
env var to bypass the file entirely in CI / containers.
Input boundary: the user prompt is passed as a JSON string to the CLI via
```
--input
```
. The CLI does NOT shell-expand the prompt; it transmits the JSON body directly to the Model API over HTTPS. No shell injection surface from prompt content.
Third-party content: image / mask / video URLs you pass are fetched by the RunComfy model server, not by the CLI on your machine. Treat external URLs as untrusted; image-based prompt injection is a known risk for any image-edit / video-edit model.
Outbound endpoints: only
```
model-api.runcomfy.net
```
(request submission) and
```
*.runcomfy.net
```
/
```
*.runcomfy.com
```
(download whitelist for generated outputs). No telemetry, no callbacks.
Generated-file size cap: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.

令牌存储：
```
runcomfy login
```
会将API令牌写入
```
~/.config/runcomfy/token.json
```
，权限为0600（仅所有者可读写）。在CI/容器环境中，可设置环境变量
```
RUNCOMFY_TOKEN
```
绕过文件存储
输入边界：用户提示词通过
```
--input
```
以JSON字符串形式传递给CLI。CLI不会对提示词进行shell扩展，而是直接通过HTTPS将JSON请求体传输给Model API。提示词内容不存在shell注入风险
第三方内容：传入的图像/蒙版/视频URL由RunComfy模型服务器获取，而非本地CLI。请将外部URL视为不可信；基于图像的提示词注入是所有图像编辑/视频编辑模型的已知风险
出站端点：仅与
```
model-api.runcomfy.net
```
（请求提交）和
```
*.runcomfy.net
```
/
```
*.runcomfy.com
```
（生成输出的下载白名单）通信。无遥测，无回调
生成文件大小限制：CLI会中止任何超过2 GiB的单个下载，防止恶意或异常模型输出占满磁盘空间

flux-2-klein

Original

Translation

🎨 Flux 2 Klein — Pro Pack on RunComfy

🎨 Flux 2 Klein — RunComfy专业套装

When to pick this model (vs siblings)

何时选择该模型（对比同类模型）

Prerequisites

前置条件

Endpoints + input schema

端点与输入 schema

`blackforestlabs/flux-2-klein/9b/text-to-image`

`blackforestlabs/flux-2-klein/9b/text-to-image`

`blackforestlabs/flux-2-klein/4b/text-to-image`

`blackforestlabs/flux-2-klein/4b/text-to-image`

Reference images (both variants)

参考图像（两个变体均支持）

How to invoke

调用方式

Prompting — what actually works

有效提示词技巧

Where it shines

适用场景

Sample prompts (verified to produce strong results)

验证有效的示例提示词

Limitations

局限性

Exit codes

退出码

How it works

工作原理

What this skill is not

本技能不包含的内容

Security & Privacy

安全与隐私