Arekejoker /

qwen21-nsfw-pose-skill

编程 Skill 图片与设计 Skill

趋势观察中

Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw

原始仓库简介 · 中文摘要待补充 · agent-skill / comfyui / image-generation / openclaw / pose-control / qwen-image

GitHub 仓库 ↗

README / 项目原文

README.md ↗抓取于 2026/10/29 14:03:23

qwen21-nsfw-pose

English | 中文

Qwen-Image 2.1 本地 NSFW / 姿势出图完整配方 — 作者级提示词结构 + NSFW LoRA + 136 个 3D 姿势库 + VNCCS 人偶精确姿势控制。

基于 ComfyUI + qwen_image_2.1_int8_convrot 底模（与 Civitai 作者同款底模），复刻并验证过 Civitai 作者样图（2026-10-12）。

适用：Claude Code / Codex / Cursor / OpenClaw（agent 技能）+ 人类手动使用
内容：可跟跑的作者案例、强制配方、姿势大胆度阶梯（L0–L3）、完整依赖与安装指南

演示（3D 人偶调姿势 → 一键生成 → 成品，Route ④）：

效果展示

本配方输出：同一海边场景的三级对照（L0 → L1 → L2）

L0 · 全着装，无 LoRA（提示词即全部）	L1 · 湿身泳装 + LoRA@1.0	L2 · 极低机位 + 湿身蹲姿 + LoRA@1.0

三张图同场景递进：L0 只有提示词；L1 加 LoRA + 显式皮肤/水珠描写；L2 再加低机位与开合姿态。LoRA 负责质感，提示词负责信息密度，机位负责大胆度。

NSFW 效果（⚠️ 以下图片包含裸露内容）

👇 点击上方卡片展开作者原图（含裸露内容 · 18+，再点收起）

作者原图（Civitai showcase，本配方复刻的目标）：

作者 · 淋浴（tawsLoRa）	作者 · 按摩（tawsLoRa）	作者 · 自拍（TheseAlpacas）

用 §「快速开始」的命令可复刻淋浴那张（复刻输出已验证与作者原图同场景同构图，见 downloads/samples/phase5_meta.json 与本文快速开始一节）。

3D 人偶精确姿势（Route ④，136 姿势库）

默认人物图 references/src_standing.png；姿势 = 骨骼旋转 JSON（MakeHuman 网格 + three.js 渲染），换姿势且保身份。姿势库来源：HuggingFace 4 个公开仓库（Totemistyk/General_Poses、 Totemistyk/Ballet_PoseStudio、MIUProject/VNCCS_PoseLibrary_Main、 MIUProject/MySuperPoseRepo）+ 55 个手工精选，共 136 个。

快速开始（作者案例跟跑）

前置安装见 install/setup.md。装好后先跑一次自检（只读，不改动任何东西）：

python3 scripts/doctor.py

它逐项检查 ComfyUI 连通性、底模/LoRA、VNCCS 节点、姿势库、浏览器后端，并给出缺失项的修复指引。全绿后一条命令复刻作者淋浴样图（~5 分钟）：

python3 scripts/qwen_pose_test.py \
  --mode t2i --name author_case_shower \
  --prompt "$(cat prompts/taws_v13_shower.txt)" \
  --seed 80964 \
  --steps 50 --cfg 2.5 --sampler er_sde --scheduler beta \
  --width 1152 --height 1728 \
  --lora "qwen2_1-femaledVaginus-nsfw-v1_3-fine_L22-31.safetensors" \
  --lora-strength 1.0 \
  --out outputs/author_case/shower.png

对比对象：downloads/samples/taws_v13_shower_author.jpg。完整元数据（提示词/参数/seed/完整工作流）：downloads/samples/phase5_meta.json。

硬件要求（参考）

底模为 Qwen-Image 2.1 int8 套件，模型文件合计约 16GB（diffusion 6.8GB / text encoder 8.7GB / VAE 0.6GB），LoRA 各自 ≤608MB。

最低：NVIDIA 12GB 显存 + 32GB 内存——能跑，ComfyUI 会自动把部分模型卸载到内存，出图慢一些
推荐：24GB 显存（3090/4090 级）+ 32–64GB 内存——模型基本常驻，体验最顺
8GB 显存：建议用 GGUF 量化版（社区实测 12–16GB 显存可跑 Q4；8GB 靠 offload 会明显更慢）
纯 CPU 不推荐（单张图耗时过长）
硬盘预留 ~40GB；CPU 无特殊要求（现代 x86_64/ARM 均可）；Linux 最省事；Windows 可原生运行基础脚本（doctor / --list-poses / 媒体锁回退，社区贡献），完整流程仍建议 WSL2；Mac（Apple Silicon）见下方单独小节
路线④额外需要一个可连接的桌面浏览器（Playwright/CDP，见 install/setup.md）

本仓库案例图与实测数据来自统一内存设备（DGX Spark）：1024×1024、40 步约 32 秒/张，峰值增量约 7–10GB。

macOS（Apple Silicon）

适用 M 系芯片（M1 及以上）；Intel Mac 不建议
模型选择看统一内存：≥32GB 直接用本仓库原版 int8 套件（ComfyUI + MPS）；16–32GB 建议改用 GGUF 量化版（搭配 ComfyUI-GGUF；社区实测 Q8 更快、Q4 更省内存）
速度预期：分钟级/张——社区报告：M5 Pro 48GB 跑 int8 约 144 秒/1024；M1 Max 64GB 约 7–10 分钟/张（加缓存优化节点如 Comfyui-Spectrum-Qwen2.1 可提速 2–3 倍）。对比本仓库 DGX Spark 实测 32 秒/张，仅供参考
已知坑：编辑模式在 MPS 上偶发 VAE 编码异常，可用 ComfyUI 的 --cpu-vae 绕过（ComfyUI issue #16433，已有修复讨论）；内存紧张时建议单张生成、关闭其他大内存应用
路线兼容：①②③ 脚本在 macOS 可直接运行（纯 Python 标准库、POSIX 兼容）；④ 需 playwright install chromium（macOS 版），install/setup.md 中的 AppArmor 提示不适用
⚠️ 以上 Mac 数据来自社区报告，维护者没有 Mac 硬件、未经实测；如果你在 Mac 上跑通或遇到问题，欢迎开 issue 反馈，我们会持续更新本说明

四条路线

需求	路线	命令
新 NSFW/性感图（文字出图）	① T2I + NSFW LoRA（必开）	`scripts/qwen_pose_test.py --mode t2i`
已有角色图换姿势（保脸/保服装）	② Edit	`scripts/qwen_pose_test.py --mode edit`
已有 3D 人偶姿势渲染图，脚本换姿势（不开浏览器）	③ 脚本姿势迁移（人偶参考 + VNCCS LoRA）	`scripts/run_pose_transfer.py --char <角色图> --pose-ref <人偶渲染图> --out <出图.png>`
指定 3D 姿势库里的精确姿势	④ VNCCS PoseStudio	`scripts/run_vnccs_ui.py --pose <name> [--prompt "<场景>"]`

路线③的人偶参考图可由路线④的运行自动保存（输出目录里的 doll_*.png），或任何 3D 姿态渲染图。不要用照片/插画当姿势参考——模型会把参考人物拼进画面，或直接重画参考人物；请使用无身份特征的 3D 人偶渲染图（路线③/④）。

姿势怎么选（大胆度阶梯 L0–L3、用户要求→姿势族映射表）：见 SKILL.md §4，或 scripts/run_vnccs_ui.py --list-poses 列出全部 136 个姿势。

配方要点（摘要）

er_sde + beta，CFG 2.5，50 步，1152×1728 竖版
NSFW LoRA 永远开（默认 femaledVaginus v1.3b @ 1.0）
提示词必须按作者结构写满 7 要素、300–1500 字符、含 LoRA 触发词
弱化配方（无 LoRA/短提示词/减步数）前必须告知用户代价，不许默默减弱

完整规则与证据：SKILL.md。

目录结构

├── SKILL.md            # agent 技能（完整规则）
├── CHANGELOG.md        # 版本变更记录
├── install/setup.md    # 安装指南（模型/LoRA/节点/姿势库）
├── scripts/            # doctor.py 自检、出图/自定义姿势脚本、浏览器 fallback、media_lock.py、validate_package.py
├── workflows/          # qwen21_t2i.json / qwen21_edit.json / VNCCS_PoseStudio_QI2.1.json
├── prompts/            # 3 篇作者原提示词 + 参数
├── references/         # 效果展示图（L0/L1/L2 海边对照）+ 默认人物图
├── downloads/samples/  # 作者原图 + 作者元数据 + 原始工作流 JSON
└── pose_library/       # 55 个手工精选姿势（安装时拷入 ComfyUI）

说明

本仓库原创代码与文档（scripts/、workflows/、prompts/、SKILL.md、README 等）采用 Apache License 2.0
第三方素材不在 Apache-2.0 覆盖范围内，权利归各自原作者：downloads/samples/ 作者原图（Civitai 作者）、pose_library/ 社区姿势与预览（MIUProject / Totemistyk，其中 Ballet 仓库为 MIT）、模型与 LoRA（HF Comfy-Org/Qwen-Image-2.1、Civitai 2986844 / 2958918 / 2988215、RunningHubAI、MIUProject 等）
NSFW 示例图仅供配方演示；仓库为公开仓库，介意图片的先收藏后阅读

致谢

本仓库的姿势控制能力（路线③④）与 136 姿势库基于 AHEKOT（VNCCS_Utils）、Totemistyk、MIUProject 的开源工作；底模与 LoRA 来自 Qwen / Comfy-Org、RunningHubAI 及 Civitai 的 tawsLoRa、TheseAlpacas、posture-v3。感谢所有作者。

README.en.md ↗抓取于 2026/10/29 14:03:23

qwen21-nsfw-pose

English | 中文

A complete local Qwen-Image 2.1 NSFW / pose pipeline — author-grade prompt structure + NSFW LoRAs + a 136-pose 3D library + precise mannequin pose control with VNCCS.

Built on ComfyUI + the qwen_image_2.1_int8_convrot base kit (the same base model the Civitai authors use). The authors' showcase images were reproduced and verified (2026-10-12).

For: Claude Code / Codex / Cursor / OpenClaw (agent skill) + manual use
Includes: runnable author cases, the mandatory recipe, boldness tiers (L0–L3), full dependencies and an install guide

Demo (deform the 3D mannequin → one-click generate → result, Route ④):

Demo: 3D mannequin deformation → live generation → result

Showcase

This recipe's output: three tiers of the same seaside scene (L0 → L1 → L2)

L0 · fully clothed, no LoRA (prompt only)	L1 · wet swimwear + LoRA@1.0	L2 · very low angle + wet squat + LoRA@1.0

Three images, same scene, escalating: L0 is prompt-only; L1 adds the LoRA plus explicit skin/water-droplet description; L2 adds the low camera angle and an open pose. The LoRA carries texture, the prompt carries information density, the camera angle carries boldness.

NSFW results (⚠️ the images below contain nudity)

Author originals (NSFW) · click the card to expand

👇 Click the card above to expand the author originals (nudity · 18+, click again to collapse)

Author originals (Civitai showcases — what this recipe targets):

Author · shower (tawsLoRa)	Author · massage (tawsLoRa)	Author · selfie (TheseAlpacas)

The shower image can be reproduced with the command under "Quick start" (the reproduction was verified to match the author original in scene and composition — see downloads/samples/phase5_meta.json and the Quick start section below).

Precise 3D mannequin poses (Route ④, 136-pose library)

Default character image: references/src_standing.png. A pose is a skeleton-rotation JSON (MakeHuman mesh, rendered with three.js), so the pose changes while identity is preserved. Pose library sources: four public HuggingFace repos (Totemistyk/General_Poses, Totemistyk/Ballet_PoseStudio, MIUProject/VNCCS_PoseLibrary_Main, MIUProject/MySuperPoseRepo) plus 55 hand-picked poses — 136 in total.

Quick start (follow the author's case)

Install first: see install/setup.md. Once installed, run the self-check (read-only, changes nothing):

python3 scripts/doctor.py

It checks ComfyUI connectivity, base models/LoRAs, VNCCS nodes, the pose library and the browser backend item by item, and prints fix instructions for anything missing. When everything is green, one command reproduces the author's shower image (~5 minutes):

python3 scripts/qwen_pose_test.py \
  --mode t2i --name author_case_shower \
  --prompt "$(cat prompts/taws_v13_shower.txt)" \
  --seed 80964 \
  --steps 50 --cfg 2.5 --sampler er_sde --scheduler beta \
  --width 1152 --height 1728 \
  --lora "qwen2_1-femaledVaginus-nsfw-v1_3-fine_L22-31.safetensors" \
  --lora-strength 1.0 \
  --out outputs/author_case/shower.png

Compare against downloads/samples/taws_v13_shower_author.jpg. Full metadata (prompt / parameters / seed / complete workflow): downloads/samples/phase5_meta.json.

Hardware requirements (reference)

The base kit is Qwen-Image 2.1 int8; model files total ~16GB (diffusion 6.8GB / text encoder 8.7GB / VAE 0.6GB), and each LoRA is ≤608MB.

Minimum: NVIDIA 12GB VRAM + 32GB RAM — it runs, but ComfyUI offloads part of the models to system memory and generation is slower
Recommended: 24GB VRAM (3090/4090 class) + 32–64GB RAM — models stay resident and it feels smooth
8GB VRAM: use a GGUF quantized build (the community reports Q4 runs in 12–16GB VRAM; 8GB with offload is noticeably slower)
Pure CPU is not recommended (a single image takes far too long)
Reserve ~40GB of disk; no special CPU requirement (any modern x86_64/ARM will do); Linux is the least fuss; on Windows the base scripts (doctor / --list-poses / media-lock fallback) run natively (community contribution), while the full pipeline is still best on WSL2; macOS (Apple Silicon) has its own section below
Route ④ additionally needs a desktop browser you can attach to (Playwright/CDP, see install/setup.md)

The showcase images and measurements in this repo come from a unified-memory machine (DGX Spark): 1024×1024, 40 steps, about 32 seconds per image, ~7–10GB peak delta.

macOS (Apple Silicon)

For M-series chips (M1 and up); Intel Macs are not recommended
Pick the model by unified memory: ≥32GB, use this repo's original int8 kit directly (ComfyUI + MPS); 16–32GB, prefer a GGUF quantized build (with ComfyUI-GGUF; the community reports Q8 is faster and Q4 saves more memory)
Speed expectation: minutes per image — community reports: M5 Pro 48GB runs int8 at ~144s per 1024px; M1 Max 64GB at ~7–10 minutes per image (cache-optimizing nodes such as Comfyui-Spectrum-Qwen2.1 can speed this up 2–3×). Compare against this repo's measured 32s per image on DGX Spark, for reference only
Known issue: edit mode occasionally hits a VAE encoding error on MPS — work around it with ComfyUI's --cpu-vae (ComfyUI issue #16433, a fix is under discussion); when memory is tight, generate one image at a time and close other memory-hungry apps
Route compatibility: the ①②③ scripts run directly on macOS (pure Python standard library, POSIX-compatible); ④ needs playwright install chromium (the macOS build), and the AppArmor note in install/setup.md does not apply
⚠️ The Mac figures above come from community reports. The maintainers have no Mac hardware and have not measured them; if you get it running on a Mac, or hit problems, please open an issue and we will keep this section updated

The four routes

Goal	Route	Command
A new NSFW/sexy image from text	① T2I + NSFW LoRA (mandatory)	`scripts/qwen_pose_test.py --mode t2i`
Change the pose of an existing character image (keep face/clothes)	② Edit	`scripts/qwen_pose_test.py --mode edit`
Change pose from a 3D mannequin render (script, no browser)	③ Scripted pose transfer (mannequin reference + VNCCS LoRA)	`scripts/run_pose_transfer.py --char <character.png> --pose-ref <mannequin_render.png> --out <result.png>`
An exact pose from the 3D library	④ VNCCS PoseStudio	`scripts/run_vnccs_ui.py --pose <name> [--prompt "<scene>"]`

Route ③'s mannequin reference can be saved automatically by a Route ④ run (the doll_*.png files in the output directory), or any 3D pose render. Do not use a photo or illustration as the pose reference — the model composites the reference person into the frame, or redraws that person entirely; use a textureless 3D mannequin render instead (Routes ③/④).

How to pick a pose (boldness tiers L0–L3, user-request → pose-family mapping): see §4 of SKILL.md, or list all 136 poses with scripts/run_vnccs_ui.py --list-poses.

Recipe highlights (summary)

er_sde + beta, CFG 2.5, 50 steps, 1152×1728 portrait
The NSFW LoRA is always on (default femaledVaginus v1.3b @ 1.0)
Prompts must follow the author's structure: all 7 elements, 300–1500 characters, including the LoRA trigger words
Weakening the recipe (no LoRA / short prompt / fewer steps) requires telling the user the cost first — never weaken it silently

Full rules and evidence: SKILL.md.

Repository layout

├── SKILL.md            # the agent skill (complete rules)
├── CHANGELOG.md        # release history
├── install/setup.md    # install guide (models / LoRAs / nodes / pose library)
├── scripts/            # doctor.py self-check, generation & custom-pose scripts, browser fallback, media_lock.py, validate_package.py
├── workflows/          # qwen21_t2i.json / qwen21_edit.json / VNCCS_PoseStudio_QI2.1.json
├── prompts/            # the 3 author prompts + their parameters
├── references/         # showcase images (L0/L1/L2 seaside set) + default character image
├── downloads/samples/  # author originals + author metadata + original workflow JSON
└── pose_library/       # 55 hand-picked poses (copied into ComfyUI at install time)

Notes

Original code and docs in this repo (scripts/, workflows/, prompts/, SKILL.md, README, …) are licensed under the Apache License 2.0
Third-party assets are not covered by Apache-2.0 and remain with their respective authors: the author originals in downloads/samples/ (Civitai authors), the community poses and previews in pose_library/ (MIUProject / Totemistyk, of which the Ballet repo is MIT), and the models and LoRAs (HF Comfy-Org/Qwen-Image-2.1, Civitai 2986844 / 2958918 / 2988215, RunningHubAI, MIUProject, …)
The NSFW sample images are for demonstrating the recipe only; this is a public repository, so if that bothers you, star it first and read later

Acknowledgements

The pose-control capability (Routes ③④) and the 136-pose library build on the open-source work of AHEKOT (VNCCS_Utils), Totemistyk and MIUProject. The base model and LoRAs come from Qwen / Comfy-Org, RunningHubAI, and tawsLoRa, TheseAlpacas and posture-v3 on Civitai. Thanks to all of them.