[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73TYATAC4YP5B22TJ0ARGKV":3,"skill-same:01M73TYATAC4YP5B22TJ0ARGKV":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M73TYATAC4YP5B22TJ0ARGKV","flux-2-klein",null,"Generate 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 \u002F Seedream 5 \u002F GPT Image 2 instead. Calls `runcomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image` (or `\u002F4b\u002F`) 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.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fflux-2-klein__skills-runcomfy-com-flux-2-klein\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: flux-2-klein\ndisplayName: \"Flux 2 Klein — Pro Pack on RunComfy\"\ndescription: >\n  Generate images with Flux 2 Klein (Black Forest Labs' distilled fast\n  variant of Flux 2) on RunComfy — bundled with the model's documented\n  prompting patterns so the skill gets sharper output than naive\n  prompting against the same model. Documents Flux 2 Klein's strengths\n  (sub-second latency, multi-reference brand styling, declarative\n  subject-first prompts), the step-count strategy (4–8 for fast\n  iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when\n  to route to Flux 2 Pro \u002F Seedream 5 \u002F GPT Image 2 instead. Calls\n  `runcomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image` (or\n  `\u002F4b\u002F`) through the local RunComfy CLI. Triggers on \"flux 2 klein\",\n  \"flux-2-klein\", \"flux klein\", \"BFL flux 2\", or any explicit ask to\n  generate with this model.\nhomepage: https:\u002F\u002Fwww.runcomfy.com\nlicense: MIT\n---\n\n# Flux 2 Klein — Pro Pack on RunComfy\n\n[runcomfy.com](https:\u002F\u002Fwww.runcomfy.com\u002F?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) · [9B model](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) · [4B model](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) · [GitHub](https:\u002F\u002Fgithub.com\u002Fagentspace-so\u002Fruncomfy-skills\u002Ftree\u002Fmain\u002Fflux-2-klein)\n\nBlack Forest Labs' **Flux 2 Klein** (the distilled, low-latency variant of Flux 2) hosted on the **RunComfy Model API** — no API key, async REST.\n\n```bash\nnpx skills add agentspace-so\u002Fruncomfy-skills --skill flux-2-klein -g\n```\n\n## When to pick this model (vs siblings)\n\nFlux 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**.\n\n| You want | Use |\n|---|---|\n| Real-time \u002F live art-direction sessions | **Flux 2 Klein 4B** |\n| Fast iteration with strong detail at the end | **Flux 2 Klein 9B** |\n| Multi-reference brand styling with consistent looks | **Flux 2 Klein** |\n| 2K–4K hero images, max resolution | Seedream 5 |\n| Maximum prompt adherence + extreme detail | Flux 2 Pro |\n| Embedded text, logos, multilingual signage | GPT Image 2 |\n| Hyperrealistic portrait | Nano Banana Pro |\n\nIf the user said \"Flux 2 Klein\" \u002F \"BFL Klein\" \u002F \"flux klein\" explicitly, route here regardless. If they said \"Flux 2\" generically, ask whether they want **Klein** (fast) or **Pro** (max quality) before defaulting.\n\n## Prerequisites\n\n1. **RunComfy CLI** — `npm i -g @runcomfy\u002Fcli`\n2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.\n3. **CI \u002F containers** — set `RUNCOMFY_TOKEN=\u003Ctoken>` instead of `runcomfy login`.\n\n## Endpoints + input schema\n\nTwo variants, same endpoint shape, same prompt grammar.\n\n### `blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image`\n\nThe fidelity-first variant. Use for polish \u002F final output.\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `prompt` | string | yes | — | Up to ~512 tokens. Longer degrades. |\n| `steps` | int | no | 25 | 4–50. **Step-distilled architecture** — 4–8 enough for concepting; ~25 for polish; >25 buys little. |\n| `width` | int | no | 1024 | 512–1536 typical. **Aspect ratio capped at 16:9**, max ~2K total. |\n| `height` | int | no | 1024 | Match `width`'s aspect intent. |\n\n### `blackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image`\n\nThe latency-first variant. Sub-second 4-step inference. Use for live iteration \u002F concepting.\n\nSame field set as 9B. Default `steps` is effectively 4 — the variant is built for that step count.\n\n### Reference images (both variants)\n\nUp to **4 simultaneous reference images** are supported on the same endpoint for style transfer \u002F guided composition. The exact field name in the JSON body is documented on the [model's API tab](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) — pass it through the CLI verbatim. Reference-image use enables editing-style workflows without a separate `\u002Fedit` endpoint.\n\n## How to invoke\n\n**Fast concepting (4B, sub-second):**\n\n```bash\nruncomfy run blackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image \\\n  --input '{\"prompt\": \"\u003Cuser prompt>\"}' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n**Polish \u002F final (9B, ~25 steps):**\n\n```bash\nruncomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image \\\n  --input '{\n    \"prompt\": \"\u003Cuser prompt>\",\n    \"steps\": 25,\n    \"width\": 1024,\n    \"height\": 1024\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n**Wide-format poster:**\n\n```bash\nruncomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image \\\n  --input '{\"prompt\": \"\u003Cuser prompt>\", \"width\": 1536, \"height\": 864}' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\nThe CLI submits, polls every 2s until terminal, then downloads any `*.runcomfy.net` \u002F `*.runcomfy.com` URL from the result into `--output-dir`. Stdout is the result JSON. Stderr is progress.\n\nFor pipe-friendly usage:\n\n```bash\nruncomfy --output json run blackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image \\\n  --input '{\"prompt\":\"...\"}' --no-wait | jq -r .request_id\n```\n\n## Prompting — what actually works\n\nThese are model-specific patterns that empirically improve output quality.\n\n**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\"`.\n\n**Specificity wins over flowery language.** \"4k product photo, softbox lighting, reflective table, 35mm, f\u002F2.8\" guides predictably. \"A really pretty product image\" doesn't.\n\n**Step-count by phase.**\n- **Concepting**: 4–8 steps on the 4B variant — sub-second feedback for live exploration.\n- **Refinement**: 8–15 steps still on 4B, locking in subject + framing.\n- **Polish**: ~25 steps on the 9B variant — texture, microdetail, fine typography.\n\n**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.\n\n**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.\n\n**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.\n\n**Anti-patterns**:\n\n- Don't conflict adjectives. \"minimalist + ornate\" cancels.\n- Don't exceed ~512 tokens. The model degrades, doesn't truncate gracefully.\n- Don't ask for 4K — the model's resolution ceiling is ~2K.\n- Don't ask for ultra-wide (>16:9) — the model crops.\n\n## Where it shines\n\n| Use case | Why Flux 2 Klein |\n|---|---|\n| **Live art-direction sessions** | Sub-second feedback (4B) enables real-time iteration |\n| **Interactive product visualization** | Fast UI previews and product comps without batch waits |\n| **Multi-reference brand styling** | Strong style consistency across references for unified asset packs |\n| **Rapid concepting → polish workflow** | 4B for exploration, 9B for the final pass — same prompt grammar throughout |\n| **Consumer-GPU-friendly inference** | 4B variant runs on modest hardware; relevant for self-host comparisons but RunComfy-hosted is fine |\n\n## Sample prompts (verified to produce strong results)\n\n**From the model page (BFL example):**\n\n```\nA vibrant hummingbird mid-flight sipping nectar from a bright pink hibiscus\nflower, iridescent emerald and sapphire feathers catching the morning sun,\nsoft bokeh tropical garden background, macro photography, razor-sharp\ndetail, cinematic lighting\n```\n\n**Product-photo pattern:**\n\n```\nA matte ceramic mug on a reclaimed-wood table, soft northern window light\nfrom the left, shallow depth of field, 50mm prime, f\u002F2.0, neutral\nbackground, e-commerce ready, 4K product photography\n```\n\n**Brand-consistent pair (multi-ref):**\n\n```\nSame composition and lighting as the reference image, but the bottle\nlabel is now blue with white sans-serif typography reading \"AURA\";\nkeep the bottle silhouette, table, and shadow exactly as in the reference\n```\n\n## Limitations\n\n- **Resolution ceiling ~2K** — for higher native res, route to Seedream 5.\n- **Aspect ratio cap 16:9** — extreme wide\u002Ftall ratios get cropped.\n- **Prompt cap ~512 tokens** — longer degrades quality; doesn't truncate gracefully.\n- **Reference image cap 4** — more than 4 increases latency and dilutes guidance.\n- **Text rendering** — the 8B Qwen3 embedder helps but GPT Image 2 still wins for embedded text precision.\n\n## Exit codes\n\nThe `runcomfy` CLI uses sysexits-style codes:\n\n| code | meaning |\n|---|---|\n| 0  | success |\n| 64 | bad CLI args |\n| 65 | bad input JSON \u002F schema mismatch (e.g. `width: 4096` would 422) |\n| 69 | upstream 5xx |\n| 75 | retryable: timeout \u002F 429 |\n| 77 | not signed in or token rejected |\n\nFull reference: [docs.runcomfy.com\u002Fcli\u002Ftroubleshooting](https:\u002F\u002Fdocs.runcomfy.com\u002Fcli\u002Ftroubleshooting?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein).\n\n## How it works\n\n1. The skill invokes `runcomfy run blackforestlabs\u002Fflux-2-klein\u002F\u003Cvariant>\u002Ftext-to-image` with a JSON body matching the schema.\n2. The CLI POSTs to `https:\u002F\u002Fmodel-api.runcomfy.net\u002Fv1\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F\u003Cvariant>\u002Ftext-to-image` with the user's bearer token.\n3. The Model API returns a `request_id`; the CLI polls `GET ...\u002Frequests\u002F\u003Cid>\u002Fstatus` every 2 seconds.\n4. On terminal status, the CLI fetches `GET ...\u002Frequests\u002F\u003Cid>\u002Fresult` and downloads any URL whose host ends with `.runcomfy.net` or `.runcomfy.com` into `--output-dir`. Other URLs are listed but not fetched.\n5. `Ctrl-C` while polling sends `POST ...\u002Frequests\u002F\u003Cid>\u002Fcancel` so you don't get billed for GPU you stopped.\n\n\n## What this skill is not\n\nNot a self-hosted Flux runner. Not a capability grant — depends on a working RunComfy account. Not multi-tenant.\n\n## Security & Privacy\n\n- **Token storage**: `runcomfy login` writes the API token to `~\u002F.config\u002Fruncomfy\u002Ftoken.json` with mode 0600 (owner-only read\u002Fwrite). Set `RUNCOMFY_TOKEN` env var to bypass the file entirely in CI \u002F containers.\n- **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.\n- **Third-party content**: image \u002F mask \u002F 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 \u002F video-edit model.\n- **Outbound endpoints**: only `model-api.runcomfy.net` (request submission) and `*.runcomfy.net` \u002F `*.runcomfy.com` (download whitelist for generated outputs). No telemetry, no callbacks.\n- **Generated-file size cap**: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.\n","# Flux 2 Klein — Pro Pack on RunComfy\n\n[runcomfy.com](https:\u002F\u002Fwww.runcomfy.com\u002F?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) · [9B model](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) · [4B model](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) · [GitHub](https:\u002F\u002Fgithub.com\u002Fagentspace-so\u002Fruncomfy-skills\u002Ftree\u002Fmain\u002Fflux-2-klein)\n\nBlack Forest Labs' **Flux 2 Klein** (the distilled, low-latency variant of Flux 2) hosted on the **RunComfy Model API** — no API key, async REST.\n\n```bash\nnpx skills add agentspace-so\u002Fruncomfy-skills --skill flux-2-klein -g\n```\n\n## When to pick this model (vs siblings)\n\nFlux 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**.\n\n| You want | Use |\n|---|---|\n| Real-time \u002F live art-direction sessions | **Flux 2 Klein 4B** |\n| Fast iteration with strong detail at the end | **Flux 2 Klein 9B** |\n| Multi-reference brand styling with consistent looks | **Flux 2 Klein** |\n| 2K–4K hero images, max resolution | Seedream 5 |\n| Maximum prompt adherence + extreme detail | Flux 2 Pro |\n| Embedded text, logos, multilingual signage | GPT Image 2 |\n| Hyperrealistic portrait | Nano Banana Pro |\n\nIf the user said \"Flux 2 Klein\" \u002F \"BFL Klein\" \u002F \"flux klein\" explicitly, route here regardless. If they said \"Flux 2\" generically, ask whether they want **Klein** (fast) or **Pro** (max quality) before defaulting.\n\n## Prerequisites\n\n1. **RunComfy CLI** — `npm i -g @runcomfy\u002Fcli`\n2. **RunComfy account** — `runcomfy login` opens a browser device-code flow.\n3. **CI \u002F containers** — set `RUNCOMFY_TOKEN=\u003Ctoken>` instead of `runcomfy login`.\n\n## Endpoints + input schema\n\nTwo variants, same endpoint shape, same prompt grammar.\n\n### `blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image`\n\nThe fidelity-first variant. Use for polish \u002F final output.\n\n| Field | Type | Required | Default | Notes |\n|---|---|---|---|---|\n| `prompt` | string | yes | — | Up to ~512 tokens. Longer degrades. |\n| `steps` | int | no | 25 | 4–50. **Step-distilled architecture** — 4–8 enough for concepting; ~25 for polish; >25 buys little. |\n| `width` | int | no | 1024 | 512–1536 typical. **Aspect ratio capped at 16:9**, max ~2K total. |\n| `height` | int | no | 1024 | Match `width`'s aspect intent. |\n\n### `blackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image`\n\nThe latency-first variant. Sub-second 4-step inference. Use for live iteration \u002F concepting.\n\nSame field set as 9B. Default `steps` is effectively 4 — the variant is built for that step count.\n\n### Reference images (both variants)\n\nUp to **4 simultaneous reference images** are supported on the same endpoint for style transfer \u002F guided composition. The exact field name in the JSON body is documented on the [model's API tab](https:\u002F\u002Fwww.runcomfy.com\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein) — pass it through the CLI verbatim. Reference-image use enables editing-style workflows without a separate `\u002Fedit` endpoint.\n\n## How to invoke\n\n**Fast concepting (4B, sub-second):**\n\n```bash\nruncomfy run blackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image \\\n  --input '{\"prompt\": \"\u003Cuser prompt>\"}' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n**Polish \u002F final (9B, ~25 steps):**\n\n```bash\nruncomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image \\\n  --input '{\n    \"prompt\": \"\u003Cuser prompt>\",\n    \"steps\": 25,\n    \"width\": 1024,\n    \"height\": 1024\n  }' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\n**Wide-format poster:**\n\n```bash\nruncomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image \\\n  --input '{\"prompt\": \"\u003Cuser prompt>\", \"width\": 1536, \"height\": 864}' \\\n  --output-dir \u003Cabsolute\u002Fpath>\n```\n\nThe CLI submits, polls every 2s until terminal, then downloads any `*.runcomfy.net` \u002F `*.runcomfy.com` URL from the result into `--output-dir`. Stdout is the result JSON. Stderr is progress.\n\nFor pipe-friendly usage:\n\n```bash\nruncomfy --output json run blackforestlabs\u002Fflux-2-klein\u002F4b\u002Ftext-to-image \\\n  --input '{\"prompt\":\"...\"}' --no-wait | jq -r .request_id\n```\n\n## Prompting — what actually works\n\nThese are model-specific patterns that empirically improve output quality.\n\n**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\"`.\n\n**Specificity wins over flowery language.** \"4k product photo, softbox lighting, reflective table, 35mm, f\u002F2.8\" guides predictably. \"A really pretty product image\" doesn't.\n\n**Step-count by phase.**\n- **Concepting**: 4–8 steps on the 4B variant — sub-second feedback for live exploration.\n- **Refinement**: 8–15 steps still on 4B, locking in subject + framing.\n- **Polish**: ~25 steps on the 9B variant — texture, microdetail, fine typography.\n\n**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.\n\n**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.\n\n**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.\n\n**Anti-patterns**:\n\n- Don't conflict adjectives. \"minimalist + ornate\" cancels.\n- Don't exceed ~512 tokens. The model degrades, doesn't truncate gracefully.\n- Don't ask for 4K — the model's resolution ceiling is ~2K.\n- Don't ask for ultra-wide (>16:9) — the model crops.\n\n## Where it shines\n\n| Use case | Why Flux 2 Klein |\n|---|---|\n| **Live art-direction sessions** | Sub-second feedback (4B) enables real-time iteration |\n| **Interactive product visualization** | Fast UI previews and product comps without batch waits |\n| **Multi-reference brand styling** | Strong style consistency across references for unified asset packs |\n| **Rapid concepting → polish workflow** | 4B for exploration, 9B for the final pass — same prompt grammar throughout |\n| **Consumer-GPU-friendly inference** | 4B variant runs on modest hardware; relevant for self-host comparisons but RunComfy-hosted is fine |\n\n## Sample prompts (verified to produce strong results)\n\n**From the model page (BFL example):**\n\n```\nA vibrant hummingbird mid-flight sipping nectar from a bright pink hibiscus\nflower, iridescent emerald and sapphire feathers catching the morning sun,\nsoft bokeh tropical garden background, macro photography, razor-sharp\ndetail, cinematic lighting\n```\n\n**Product-photo pattern:**\n\n```\nA matte ceramic mug on a reclaimed-wood table, soft northern window light\nfrom the left, shallow depth of field, 50mm prime, f\u002F2.0, neutral\nbackground, e-commerce ready, 4K product photography\n```\n\n**Brand-consistent pair (multi-ref):**\n\n```\nSame composition and lighting as the reference image, but the bottle\nlabel is now blue with white sans-serif typography reading \"AURA\";\nkeep the bottle silhouette, table, and shadow exactly as in the reference\n```\n\n## Limitations\n\n- **Resolution ceiling ~2K** — for higher native res, route to Seedream 5.\n- **Aspect ratio cap 16:9** — extreme wide\u002Ftall ratios get cropped.\n- **Prompt cap ~512 tokens** — longer degrades quality; doesn't truncate gracefully.\n- **Reference image cap 4** — more than 4 increases latency and dilutes guidance.\n- **Text rendering** — the 8B Qwen3 embedder helps but GPT Image 2 still wins for embedded text precision.\n\n## Exit codes\n\nThe `runcomfy` CLI uses sysexits-style codes:\n\n| code | meaning |\n|---|---|\n| 0  | success |\n| 64 | bad CLI args |\n| 65 | bad input JSON \u002F schema mismatch (e.g. `width: 4096` would 422) |\n| 69 | upstream 5xx |\n| 75 | retryable: timeout \u002F 429 |\n| 77 | not signed in or token rejected |\n\nFull reference: [docs.runcomfy.com\u002Fcli\u002Ftroubleshooting](https:\u002F\u002Fdocs.runcomfy.com\u002Fcli\u002Ftroubleshooting?utm_source=skills.sh&utm_medium=skill&utm_campaign=flux-2-klein).\n\n## How it works\n\n1. The skill invokes `runcomfy run blackforestlabs\u002Fflux-2-klein\u002F\u003Cvariant>\u002Ftext-to-image` with a JSON body matching the schema.\n2. The CLI POSTs to `https:\u002F\u002Fmodel-api.runcomfy.net\u002Fv1\u002Fmodels\u002Fblackforestlabs\u002Fflux-2-klein\u002F\u003Cvariant>\u002Ftext-to-image` with the user's bearer token.\n3. The Model API returns a `request_id`; the CLI polls `GET ...\u002Frequests\u002F\u003Cid>\u002Fstatus` every 2 seconds.\n4. On terminal status, the CLI fetches `GET ...\u002Frequests\u002F\u003Cid>\u002Fresult` and downloads any URL whose host ends with `.runcomfy.net` or `.runcomfy.com` into `--output-dir`. Other URLs are listed but not fetched.\n5. `Ctrl-C` while polling sends `POST ...\u002Frequests\u002F\u003Cid>\u002Fcancel` so you don't get billed for GPU you stopped.\n\n\n## What this skill is not\n\nNot a self-hosted Flux runner. Not a capability grant — depends on a working RunComfy account. Not multi-tenant.\n\n## Security & Privacy\n\n- **Token storage**: `runcomfy login` writes the API token to `~\u002F.config\u002Fruncomfy\u002Ftoken.json` with mode 0600 (owner-only read\u002Fwrite). Set `RUNCOMFY_TOKEN` env var to bypass the file entirely in CI \u002F containers.\n- **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.\n- **Third-party content**: image \u002F mask \u002F 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 \u002F video-edit model.\n- **Outbound endpoints**: only `model-api.runcomfy.net` (request submission) and `*.runcomfy.net` \u002F `*.runcomfy.com` (download whitelist for generated outputs). No telemetry, no callbacks.\n- **Generated-file size cap**: the CLI aborts any single download > 2 GiB to prevent disk-fill from a malicious or runaway model output.\n",{"name":5,"license":15,"homepage":24,"description":25,"displayName":26},"https:\u002F\u002Fwww.runcomfy.com","Generate 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 \u002F Seedream 5 \u002F GPT Image 2 instead. Calls `runcomfy run blackforestlabs\u002Fflux-2-klein\u002F9b\u002Ftext-to-image` (or `\u002F4b\u002F`) 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.\n","Flux 2 Klein — Pro Pack on RunComfy","master","63f17866001c5ca854bf2fa0b678ce277133de5b","skills\u002Fmarketplace\u002Fflux-2-klein__skills-runcomfy-com-flux-2-klein",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill flux-2-klein",{"tool":43,"command":44},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill flux-2-klein",{"tool":46,"command":47},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill flux-2-klein","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fflux-2-klein__skills-runcomfy-com-flux-2-klein\u002FSKILL.md",true,[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"skill-report.json","REFERENCE","参考文档",63667,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fflux-2-klein__skills-runcomfy-com-flux-2-klein\u002Fskill-report.json",[58,66,73,80,87,94],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":65},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":65},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":65},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":65},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":65},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":65},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]