qwen21-nsfw-pose
Use when generating sexy/NSFW or posed images with local Qwen-Image 2.1 — pose/NSFW LoRAs (tawsLoRa femaledVaginus, TheseAlpacas, posture-v3), pose transfer from an existing image, or exact pose control via VNCCS PoseStudio 3D pose library. Triggers: 性感姿势, 摆姿势, NSFW 出图, 换姿势, 姿势控制, pose transfer, pose lora, VNCCS, 人偶姿势, 姿势库. Independent of any general image-generation skill (which handles SFW text/edit/cutout work).
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/arekejoker--qwen21-nsfw-pose-skill)HTML
<a href="/listings/arekejoker--qwen21-nsfw-pose-skill"><img src="/api/listings/arekejoker--qwen21-nsfw-pose-skill/badge.svg" alt="findsafeskills safety rating" /></a>Install
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 403 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- ---
- name: qwen21-nsfw-pose
- description: Use when generating sexy/NSFW or posed images with local Qwen-Image 2.1 — pose/NSFW LoRAs (tawsLoRa femaledVaginus, TheseAlpacas, posture-v3), pose transfer from an existing image, or exact pose control via VNCCS PoseStudio 3D pose library. Triggers: 性感姿势, 摆姿势, NSFW 出图, 换姿势, 姿势控制, pose transfer, pose lora, VNCCS, 人偶姿势, 姿势库. Independent of any general image-generation skill (which handles SFW text/edit/cutout work).
- license: Apache-2.0
- ---
- # Qwen-Image 2.1 NSFW / Pose Pipeline
- Local photorealistic NSFW + pose control: ComfyUI + Qwen-Image 2.1 (int8 convrot)
- + NSFW LoRAs + a 136-pose VNCCS 3D pose library.
- **Path convention:** everything in this skill is relative to the skill root
- (this directory). Scripts in `scripts/`, workflow graphs in `workflows/`,
- author prompts in `prompts/`, reference images in `references/`,
- author sample data (originals + metadata) in `downloads/samples/`.
- ComfyUI-side locations (models, LoRAs, pose library) are configurable via env
- vars — see `install/setup.md` and §2. The default host for ComfyUI is
- `http://127.0.0.1:8188` (override with `COMFYUI_URL`).
- This file is self-contained: setup, recipe, pose selection, and a first-run
- author case are all inside.
- ## 0. First run — follow the author's case (recommended)
- The fastest way to trust the pipeline is re-running the author's own sample
- prompt and comparing against the author's published image (verified 2026-10-12):
- ```bash
- 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
- ```
- - Other cases: `prompts/taws_v13_massage.txt` (30 steps, same seed, per its
- `.params.json`) and `prompts/thesealpacas_v2_selfie.txt` (CFG 4.0 +
- `thesealpacas-nsfw-v2` @0.8; its `.txt` ends with a `[negative]` section —
- pass that to `--negative`).
- - Author originals to compare against: `downloads/samples/*_author.jpg`
- (shower / massage / selfie). Full author metadata (prompts/params/seed/
- complete ComfyUI graph) in `downloads/samples/phase5_meta.json`.
- ## 1. Routing
- | Request | Route | Tool |
- | --- | --- | --- |
- | New sexy/NSFW image from a text idea | ① T2I + NSFW LoRA (mandatory) | `scripts/qwen_pose_test.py --mode t2i` |
- | Change 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 Pose transfer | `scripts/run_pose_transfer.py` |
- | Exact pose from the 3D pose library (136 poses) | ④ VNCCS PoseStudio | `scripts/run_vnccs_ui.py` (browser automation) |
- | Do NOT use: a plain photo or illustration as pose reference — the model composites it as a second person, or redraws the reference person entirely (tested twice); use a textureless 3D mannequin render with route ③/④ instead | | |
- Outputs land under `./outputs/` (the scripts create directories as needed).
- ## 2. Setup — what this package contains and what to install
- ### 2.1 In this package
- | Path | Content |
- | --- | --- |
- | `SKILL.md` | this file |
- | `scripts/` | `doctor.py` (read-only environment self-check: ComfyUI, models, LoRAs, VNCCS, pose library, browser stack — every check degrades to WARN/SKIP with a fix hint), `qwen_pose_test.py` (routes ①②), `run_pose_transfer.py` (route ③: pose transfer from a 3D mannequin render, no browser), `run_vnccs_ui.py` (route ④), `make_custom_pose.py` (new pose from a library pose by bone rotation), `run_phase5.py` + `build_phase5_sheet.py` (case re-run & comparison sheet), `media_lock.py` (shared media lock, bundled), `browser_fallback.py` (standalone CDP fallback when the OpenClaw adapter is absent), `validate_package.py` (offline package integrity check) |
- | `workflows/` | `qwen21_t2i.json`, `qwen21_edit.json` (official Qwen-Image 2.1 graphs), `VNCCS_PoseStudio_QI2.1.json` |
- | `prompts/` | the 3 author prompts + `.params.json` (the exact local-test settings) |
- | `references/` | `pose_examples/` (L0/L1/L2 seaside examples), `src_standing.png` (default character for route ④) |
- | `downloads/samples/` | author originals `*_author.jpg` (shower/massage/selfie) + `phase5_meta.json` (prompt, params, seed, complete graph JSONs) + the 3 raw ComfyUI graph files — used by `scripts/run_phase5.py` & `build_phase5_sheet.py` |
- | `pose_library/local_user_poses/Uncategorized/` | 55 curated extra pose JSONs + previews — copy into ComfyUI's `PoseLibrary/local_user_poses/Uncategorized/` after installing the node |
- | `install/setup.md` | full install guide (models, LoRAs, node, pose repos, commands) |
- ### 2.2 ComfyUI-side dependencies (see `install/setup.md` for exact commands)
- - **Base models (3 files)** from HF `Comfy-Org/Qwen-Image-2.1`:
- `diffusion_models/qwen_image_2.1_int8_convrot.safetensors`,
- `text_encoders/qwen3vl_8b_int8_convrot.safetensors`,
- `vae/qwen_image_2.1_vae_bf16.safetensors` — into the ComfyUI model dirs.
- - **LoRAs** (into ComfyUI `models/loras/`):
- | File (size) | Use | Source |
- | --- | --- | --- |
- | `qwen2_1-femaledVaginus-nsfw-v1_3-fine_L22-31.safetensors` (608M) | default: anatomy + pose, sharpest | Civitai model 2986844 — tawsLoRa "Qwen Image 2.1 - FemaledVaginus-NSFW" |
- | `qwen2_1-femaledVaginus-nsfw-v1.3-fine.safetensors` (608M) | same family, v1.3 | Civitai model 2986844 |
- | `thesealpacas-nsfw-v2.safetensors` (79.7M) | most reveal, "influencer" face drift | Civitai model 2958918 |
- | `nsfw-posture-v3.safetensors` (84M) | strongest pose/body emphasis | Civitai model 2988215 |
- | `qwen21-nsfw-image-edit.safetensors` (84M) | edit-route undress/pose changes | HF `RunningHubAI/Qwen-Image-2.1-NSFW-Image-Edit` (mirror of oreolove "Nude Edit"; original Civitai page delisted) |
- | `VNCCS_QI2_PoseStudioV1.1.safetensors` (159M) | routes ③ and ④ (file name selectable via the `VNCCS_LORA` env var) | HF `MIUProject/VNCCS_PoseStudio_QI2.1` (same repo as the workflow JSON) |
- - **VNCCS_Utils custom node**: https://github.com/AHEKOT/ComfyUI_VNCCS_Utils →
- clone into `ComfyUI/custom_nodes/`, then restart ComfyUI once.
- - **Pose library**: 4 HuggingFace repos (the public catalog as of 2026-10-12):
- `Totemistyk/General_Poses_PoseStudio` (50), `Totemistyk/Ballet_PoseStudio`
- (3 in manifest; the repo actually ships 58 — register + refresh, then copy
- this package's 55 curated extras into `local_user_poses/Uncategorized/`),
- `MIUProject/VNCCS_PoseLibrary_Main` (16), `MIUProject/MySuperPoseRepo` (12).
- Register: `curl -X POST 127.0.0.1:8188/vnccs/pose_library/repositories/add
- -d '{"repo_id":"<owner>/<repo>"}'`. Total after setup: 136.
- **A repo refresh deletes local files not in the remote manifest** — extra/
- curated poses belong in `PoseLibrary/local_user_poses/<Category>/`
- (always listed, never auto-cleaned). Pose list API: `GET /vnccs/pose_library/list`.
- - **Route ④ extras**: any CDP Chrome (default `127.0.0.1:18800`) +
- `browser_client.py` + playwright. On the original host these live in
- `~/.openclaw/tools/browser/`; elsewhere point `run_vnccs_ui.py` at an
- equivalent CDP endpoint (it only needs `connect_sync(playwright)` to return a
- browser with one context — a minimal stand-in is fine).
- - **media_lock**: bundled in `scripts/`; both scripts import it first from the
- package, then fall back to `~/.openclaw/tools`.
- The base model is `qwen_image_2.1_int8_convrot.safetensors` — the same model
- the Civitai authors of these LoRAs used, so their published prompts/params
- transfer well. (Note: one of the three author samples actually ran on a
- different base with 5 stacked LoRAs; we reproduced it with the single
- thesealpacas-v2 LoRA on the convrot base — see Parameter provenance below.)
- Download tips (verified): Civitai via the official CLI or
- `curl -H "Authorization: Bearer <token>" <file-url>`; HuggingFace via
- `hf-mirror.com` directly (no proxy — a proxy causes SSL_ERROR).
- ## 3. Route ① — T2I (the "author recipe", validated 2026-10-12)
- ### 3.1 Mandatory recipe — do not weaken silently
- This recipe reproduces Civitai showcase-level results. **All of the following are
- part of the recipe; a deviation changes the result and must be told to the user:**
- - **Sampler** `er_sde` + scheduler `beta` (not euler/simple)
- - **CFG 2.5** (the A1 reference; 2.5–4 works, CFG 1 starves the LoRA)
- - **Steps = the reference sample's value: 50** (A1 provenance, table below)
- - **Size 1152×1728 portrait 2:3** (`--width 1152 --height 1728`); keep
- `--resolution 1024` (that flag feeds `TextEncodeQwenImage21`, it is not pixel size)
- - **A LoRA is always on for route ①.** Default:
- `qwen2_1-femaledVaginus-nsfw-v1_3-fine_L22-31.safetensors` @ **1.0**
- - **The prompt is the main lever** — it must follow the author structure
- (§3.2) at the author's density (300–1500 characters, explicit terms).
- Short/keyword prompts and SFW-generic phrasing are what make output look bland.
- - **Pass the reference sample's seed** when you claim "reproduction"
- (A1 seed = 80964). The harness default seed (424242) is fine for new
- creative runs but must not be labelled as the author's result.
- Parameter provenance (source: `scripts/run_phase5.py` + each run's `*.png.json`):
- | Run record | Steps | CFG | Seed | LoRA strength (local test) |
- | --- | --- | --- | --- | --- |
- | A1 shower (primary reference) | 50 | 2.5 | 80964 | 1.0 |
- | A2 massage (separate sample) | 30 | 2.5 | 80964 | 1.0 |
- | B1 selfie | 50 | 4.0 | 124880844757561 | 0.8 (thesealpacas-v2) |
- | C1 control | 50 | 2.5 | 80964 | no LoRA |
- Preserve each sample's settings as a unit; do not mix one sample's prompt with
- another sample's params and present it as "the author recipe".
- ### 3.2 Prompt structure (copy the pattern, fill the scene)
- The working prompts all contain, in this order — write all 7, no omissions:
- 1. Camera: "A hyper-realistic photograph / low-angle shot / top-down overhead shot", lens and angle
- 2. Subject: age, build, hair (color, wet/dry, placement)
- 3. Pose: pick one from the pose ladder (§4) and spell out each limb (which leg bent, where the hands are, what the head/gaze does)
- 4. Setting + lighting: "warm steamy light", "neon bokeh", "soft morning light through sheer curtains"
- 5. Skin: "glistening", "visible pores", "natural skin texture", "slick oily sheen"
- 6. Anatomy/reveal where desired — the LoRAs were trained on explicit terms
- (e.g. "labia majora ... innie distinctly visible"); generic words ("seductive")
- do almost nothing
- 7. Finish: "8k resolution, cinematic lighting, candid 'caught in the moment'
- atmosphere, photorealistic anatomy"
- Template (a real author prompt runs 300–1500 chars):
- ```
- A hyper-realistic, {camera} shot {subject with age/build/hair state},
- {one pose from §4, limb by limb}. {Setting + lighting}. Her skin is
- {glistening/visible pores/slick oily sheen}. {explicit anatomy/reveal wording}.
- {face/expression}. 8k resolution, cinematic lighting, candid "caught in the
- moment" atmosphere, photorealistic anatomy.
- ```
- **Before writing, load a verified author prompt and rewrite it for your scene** —
- `prompts/*.txt` (+ matching `.params.json`). Writing from scratch is what makes
- results look generic.
- ### 3.3 Deviations — tell, don't silently do it
- If the user asks for a shorter prompt, a SFW-generic prompt, "no LoRA", fewer
- steps, or a different sampler — **and** if you (the agent) ever need to deviate
- from the recipe for any reason (model refuses a token, out-of-memory, etc.):
- say the expected cost out loud, show the evidence, and proceed only after
- confirmation. Never present a weakened run as "the recipe's result"; label what
- was changed next to the delivered image. Evidence to cite:
- - **True controlled experiment (single variable = LoRA):** `C1` (author prompt,
- 50 steps, seed 80964, **no LoRA**) vs `A1` (identical prompt/params + LoRA):
- no-LoRA still looks showcase-grade as a photograph, but the LoRA is what adds
- the skin/gloss/anatomy detail the author's images have. So "no LoRA" ≈
- "good photograph, not the author's texture".
- - **Visual demo (multiple variables: prompt + outfit + LoRA + seed):**
- `references/pose_examples/01_seaside.png` (L0, no LoRA) vs
- `01b_seaside_lora.png` (L1 + LoRA) vs `06_l2_squat_lowangle.png`
- (L2 + low angle + LoRA) — shows the ladder of how much the full recipe adds.
- It demonstrates the effect but does **not** isolate any single factor.
- ### 3.4 Known limits of the harness
- - **One LoRA per run.** `qwen_pose_test.py` injects a single `LoraLoaderModelOnly`
- (node id 99) between `UNETLoader` and `KSampler`. Civitai showcase workflows
- often stack 3–5 LoRAs; to reproduce those, chain extra `LoraLoaderModelOnly`
- nodes in `build_workflow()`.
- - **No refine pass / no EasyCache.** Authors add a 2× lanczos upscale + a 25-step
- `denoise 0.35` pass and `EasyCache`; `QwenImage21Cache` is broken on the
- original host (`aimdo memory compile error`) and the route ④ runner removes it.
- A/B runs matched the authors' look without the refine pass — add it only when
- a job needs extra sharpness.
- ## 4. Pose selection (the "boldness scale") — match the user's request
- Read the user's request (clothes state, desired mood, scene) → pick a tier →
- give a **concrete pose**, not a vague one. "Bold" is three levers combined:
- **pose openness × camera angle × clothing/wet state**.
- ### 4.1 Tiers (English wording to use in route ① prompts)
- - **L0 closed / editorial** (clothed SFW): standing with weight on one leg, hand
- on hip or in pocket; sitting on a chair, legs crossed at the ankles; leaning on
- a railing/wall, looking back over the shoulder; mid-stride walking.
- - **L1 open** (swimwear / wet / relaxed): crouching with knees apart, hands on
- the floor; sitting on the floor with knees opened to one side; lying on her
- side in bed, propped on an elbow, looking back over the shoulder; kneeling with
- hands behind; reclining on a sofa with legs open.
- - **L2 bold** (author style — always pair with the NSFW LoRA + low angle):
- standing with legs apart, shot from a low angle looking up; lying prone with
- hips lifted toward the camera; sitting with legs wide open, leaning forward on
- the elbows; kneeling on one knee with the other leg extended to the side, torso
- arched back; lying on her back with legs open, one hand behind the head.
- - **L3 extreme / cropped**: extreme low angle looking up between open legs;
- overhead shot lying flat with legs open; cropped framing (waist-up or
- mid-thigh) to emphasize the pose.
- ### 4.2 Suggestion table (user request → tier → concrete pose)
- | User asks for (examples) | Tier | Route ④ library pose families (`--list-poses` names) | Route ① prompt wording |
- | --- | --- | --- | --- |
- | 全着装、自然/编辑感 (standing, portrait, office/street) | L0 | Standing / Sitting / Walking / Close Up | standing with weight on one leg, hand in pocket; seated on a chair, legs crossed at the ankles |
- | 泳装/湿身/海滩/浴室 (swimwear, wet, relaxed) | L1 | Squatting / Kneeling / Laying Back | crouching with knees apart, hands on the floor, looking back over the shoulder |
- | 大胆/NSFW (nude + LoRA, low angle, "author style") | L2 | Kneeling / Laying Back / Prone / Splits / Crawling / Dancing on knees | standing with legs apart from a low angle; prone with hips lifted toward the camera; seated wide, leaning forward on elbows |
- | 极端/特写构图 (crop, extreme low, overhead) | L3 | Splits / any L2 family + crop framing | extreme low angle looking up between open legs; overhead, lying flat with legs open |
- Rules:
- 1. Decide the reveal first: clothed → L0; swimwear/wet → L1; nude + NSFW LoRA → L2.
- **Pairing the LoRA with an L0 pose is the most common cause of "bland" NSFW
- output** (observed, not a proven law).
- 2. Camera angle amplifies the pose (empirical heuristic): low angle ≈ +1
- boldness, overhead ≈ +1. "Low angle + L1" ≈ "eye level + L2" — this is why
- the author's shower/massage shots read as bold despite simple poses.
- 3. One pose per prompt, limb by limb; two competing pose descriptions get blended.
- 4. When the user names a pose they saw somewhere, search the library first:
- `python3 scripts/run_vnccs_ui.py --list-poses` (136 entries with file paths).
- ## 5. Route ② — Edit (pose change with identity preservation)
- ```bash
- python3 scripts/qwen_pose_test.py \
- --mode edit --name pose_change --input /absolute/base.png \
- --prompt "change her pose to kneeling on one knee, hands on hips, keep face hair and outfit" \
- --cfg 3 --sampler er_sde --scheduler beta --steps 20 \
- --out outputs/pose_change.png
- ```
- CFG 3 is more stable for edit mode. SFW instruction prompts keep NSFW LoRAs from
- triggering; add `--lora qwen21-nsfw-image-edit.safetensors` only when undressing.
- ## 6. Route ③ — Scripted pose transfer (3D mannequin reference)
- ```bash
- python3 scripts/run_pose_transfer.py \
- --char /absolute/character.png \
- --pose-ref /absolute/doll_render.png \
- --out outputs/pose_transfer.png [--seed N] [--steps 25]
- ```
- The pose source must be a textureless **3D mannequin render** — e.g. the
- `doll_*.png` captures that route ④ saves under the ComfyUI output dir, or any
- 3D poser render of the target pose. Photos and illustrations as pose references
- do NOT work: the model composites the reference person as a second person, or
- redraws the reference person entirely (retested 2026-10-16 — all variants
- failed).
- Verified recipe (2026-10-16) — the script sets it up automatically:
- - dual-image edit with **image 1 = mannequin** (pose) and **image 2 = character** (identity);
- - prompt `replace the pose of <image 2> with the pose of <image 1>. keep the character of <image 2>`;
- - **VNCCS PoseStudio LoRA @ 1.0 is mandatory** — without it the mannequin is
- ignored entirely (3 no-LoRA controls);
- - 25 steps, cfg 1, euler/simple, 1024 px. Single person, identity kept, pose
- follows the render; stable across seeds (sit ×3 seeds + crawling /
- kneel-side / lean-back all passed). Camera framing can differ slightly from
- the render; producing *new* mannequin renders still requires a route ④
- browser session — route ③ reuses captures you already have.
- ## 7. Route ④ — VNCCS PoseStudio (exact pose from the 3D library)
- The `VNCCS_PoseStudio` node needs the ComfyUI **web frontend** for its 3D "live
- capture"; the headless API fails with "Live capture timed out". So the runner
- drives a CDP browser: load the official graph → set character image + pose
- JSON → queue → collect outputs from disk. ~60–90 s each.
- ```bash
- # list all 136 poses with resolved file paths
- python3 scripts/run_vnccs_ui.py --list-poses
- # run one pose on a character image (+ optional scene prompt)
- python3 scripts/run_vnccs_ui.py --pose "squatting leaning back" \
- [--char /absolute/face.png] [--prompt "on a rooftop at night, city bokeh"] [--timeout 900]
- ```
- - `--pose` takes the name/slug case-insensitively (`crawling`, `Squatting
- Leaning Back`, `arabesque`). 9 names exist in more than one repository
- (`Standing A`, `CloseUp A`, …); qualify with `<repo>/<category>/<name>`
- (exact keys printed by `--list-poses`, e.g.
- `miuproject_vnccs_poselibrary_main/standing/standing_a`).
- - **Scene prompt (`--prompt`):** the capture prompt is rebuilt at execution
- time from the scene document's `export` block (default template
- `Draw character from image2\n<lighting>\n<user_prompt>`); `--prompt "..."`
- injects `export.user_prompt` before the graph loads. Editing the
- `TextEncodeQwenImage21` widget or adding `export.user_prompt` to a *library
- pose file* has no effect. To change the scene of an existing route ④ result,
- re-run it through route ② (`qwen_pose_test.py --mode edit`).
- - The runner reaches a CDP browser through the OpenClaw adapter when present,
- otherwise through the bundled `scripts/browser_fallback.py` (reuses a
- reachable `COMFY_BROWSER_CDP` endpoint, else launches a throwaway headless
- Chromium; `COMFY_BROWSER_MODE=auto|attach|launch`).
- - The runner re-indexes the pose library on every call — newly downloaded poses
- are usable immediately. Each run writes `<pose>_<stamp>.meta.json` next to
- the outputs and never clobbers previous results (unique comfy prefix per run).
- - Output: `./outputs/vnccs_ui/` (override with `VNCCS_UI_OUT`). The 3D doll is a
- bare MakeHuman mannequin — nude prompts + pose transfer can produce nude
- output (expected: the model reads the doll's state).
- - **Custom poses from code:** `scripts/make_custom_pose.py` loads a library
- pose into the PoseStudio editor, adds bone rotations, and saves through the
- editor's own Save (JSON + preview in
- `PoseLibrary/local_user_poses/poses/<category>/`). The new pose works with
- `run_vnccs_ui.py --pose` at once. `--list-bones` prints the base pose's
- euler angles; pass the full library id when a name is not unique.
- ```bash
- python3 scripts/make_custom_pose.py \
- --base "MIUProject__VNCCS_PoseLibrary_Main/poses/Standing/Standing A" \
- --name "Arms Out" --rotate upperarm_l:1:90 --rotate upperarm_r:1:-90
- ```
- - **Pose fidelity caveat:** each pose JSON carries its own `cameraParams`
- (yaw/pitch/zoom); the generated image inherits that viewpoint. Poses whose
- shape only reads from another angle (e.g. a true arabesque's extended back
- leg) come out front-facing and ambiguous — rotate the doll in the UI and
- re-run, or pick a pose that reads from the front.
- ## 8. Environment & Safety
- - ComfyUI as a service (original host: `systemctl --user status|restart
- comfyui.service`). After installing new custom nodes, one restart is required.
- - The route scripts take the bundled media lock in shared mode
- (`media_lock(exclusive=False, wait_timeout=...)`) so they don't fight video
- jobs on a shared machine; route ④ wraps the whole browser run in it.
- - On the original host, video tasks hold the lock exclusively (~06:45 / 09:00 /
- 11:30 openclaw windows); expect waits, not conflicts.
- - If a graph includes `QwenImage21Cache` and the host errors on it
- (`aimdo memory compile error`), remove the node and rewire LoRA → KSampler
- (the route ④ runner does this automatically in the browser).
- - Never modify the workflow JSONs in this package's `workflows/` while a run is
- in flight; the harness works on in-memory copies anyway.
- - A 50-step 1152×1728 run takes ~200–400 s on the int8 model; a 30-step edit
- run ~60–120 s.
- ## 9. Verification
- 1. Check the harness printed `ok: true` and the output file is non-empty.
- 2. Visually inspect with an image-reading tool (composition, pose match,
- anatomy, face). For pose-transfer runs, compare against the reference.
- 3. For reproductions of published images, compare side-by-side with the author
- original (`downloads/samples/*_author.jpg`; comparison-sheet
- example: `scripts/build_phase5_sheet.py`).
- 4. Record prompt/seed/steps/LoRA in the run's `*.json` meta file (harnesses
- write one automatically for routes ①②③④).
- 5. When a recipe deviation was made (weaker prompt, no LoRA, fewer steps,
- default seed), label the output and state the deviation next to it in the
- delivery message.
- Last full verification: 2026-10-12 — route ① (4 author-prompt reproductions),
- route ② (9/9 pose edits with identity preserved), route ④ (6 pose runs:
- crawling, kneeling side, leaning back, sitting side, squatting leaning back,
- arabesque — the last one verified for output only, pose-shape match unverified;
- its doll capture turned out to be a stale legacy capture),
- pose index count 136 == `GET /vnccs/pose_library/list`, pose-ladder A/B images
- in `references/pose_examples/`.
- Follow-up checks 2026-10-14: route ④ `--prompt` (scene follows the prompt, pose
- preserved), bundled browser fallback launch path, and custom pose creation via
- `scripts/make_custom_pose.py` (save + output verified).
- Follow-up checks 2026-10-16 (route ③): 6 mannequin-reference transfers passed
- (sit ×3 seeds, crawling, kneel-side, lean-back): single person, identity kept,
- pose follows the render; 3 no-LoRA controls ignored the mannequin; photo and
- illustration references still fail (composite / redraw of the reference
- person). Script `scripts/run_pose_transfer.py` added and end-to-end tested.
README.md · README · 148 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- # qwen21-nsfw-pose
- [](https://github.com/Arekejoker/qwen21-nsfw-pose-skill/actions/workflows/validate.yml)
- [English](README.en.md) | 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):
- <img src="references/demo_pose_studio.gif" width="100%" alt="演示:3D 人偶变形 → 实时生成 → 成品" />
- ---
- ## 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 |
- | --- | --- | --- |
- | <img src="references/pose_examples/01_seaside.png" width="290" /> | <img src="references/pose_examples/01b_seaside_lora.png" width="290" /> | <img src="references/pose_examples/06_l2_squat_lowangle.png" width="290" /> |
- 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)
- <details>
- <summary><picture><img src="references/author_samples_cover_cursor.gif?v=3" width="100%" alt="作者原图(NSFW)· 点击卡片展开" /></picture><br/><b>👇 点击上方卡片展开作者原图(含裸露内容 · 18+,再点收起)</b></summary>
- **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) |
- | --- | --- | --- |
- | <img src="downloads/samples/taws_v13_shower_author.jpg" width="300" /> | <img src="downloads/samples/taws_v13_massage_author.jpg" width="300" /> | <img src="downloads/samples/thesealpacas_v2_selfie_author.jpg" width="300" /> |
- </details>
- 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](install/setup.md)。装好后先跑一次自检(只读,不改动任何东西):
- ```bash
- 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):
- ```bash
- 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](LICENSE)
- - 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](https://github.com/AHEKOT/ComfyUI_VNCCS_Utils)(VNCCS_Utils)、[Totemistyk](https://huggingface.co/Totemistyk)、[MIUProject](https://huggingface.co/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。
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.