flux-2-kleinGenerate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-reference brand styling, declarative subject-first prompts), the step-count strategy (4–8 for fast iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when to route to Flux 2 Pro / Seedream 5 / GPT Image 2 instead. Calls `runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image` (or `/4b/`) through the local RunComfy CLI. Triggers on "flux 2 klein", "flux-2-klein", "flux klein", "BFL flux 2", or any explicit ask to generate with this model.
Install via ClawdBot CLI:
clawdbot install kalvinrv/flux-2-kleinGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://model-api.runcomfy.net/v1/models/blackforestlabs/flux-2-klein/<variantCalls external URL not in known-safe list
https://www.runcomfy.comAudited May 1, 2026 · audit v1.0
Generated May 12, 2026
Marketing teams iterate on ad creatives live with stakeholders, generating dozens of variations in seconds using the 4B sub-second latency. This enables rapid A/B testing of visual concepts before committing to high-res production.
Online retailers generate consistent, branded product images across multiple variants (angles, backgrounds, lighting) using multi-reference style transfer. The 9B model provides polished final images for listings.
Artists and museums deploy generative art installations where visitors prompt live image creation on large displays. The sub-second feedback loop of the 4B variant keeps the experience engaging.
Game studios rapidly prototype character designs, environments, and props using subject-first prompts. The step-strategy allows quick ideation at 4-8 steps and final polish at 25 steps.
Print-on-demand platforms integrate the skill to let users design custom T-shirts, mugs, and posters with brand-consistent styling. Reference images ensure logos and color schemes are faithfully reproduced.
Offer a metered API where users pay per image generation, with tiers based on model variant (4B vs 9B) and monthly usage limits. Higher tiers include priority queuing and additional reference image slots.
License the skill to large marketing agencies or e-commerce platforms for internal use, with custom SLAs, dedicated CLI endpoints, and training for their creative teams. Revenue is from annual contracts.
Integrate the skill as a white-label text-to-image widget inside existing design tools (e.g., Canva, Figma plugins) or e-commerce platforms. Charge per generation or a flat monthly fee to the platform operator.
💬 Integration Tip
To get started, install the RunComfy CLI via npm, run `runcomfy login` for device-code auth (or set RUNCOMFY_TOKEN in CI), and test a simple generation with `runcomfy run blackforestlabs/flux-2-klein/4b/text-to-image --input '{"prompt":"a cat"}' --output-dir ./outputs`.
Scored May 12, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。