✨ Qwen-Image 2.1 After Dark — 4-Mode Auto-Prompt Glamour Workflow (NSFW) — 12 GB+ (recommended 16 GB)

ComfyUI · Qwen-Image 2.1 · one control panel · Built with Qwen

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🔞 Mature content (18+). This is the adult version of my SFW workflow: https://civarchive.com/models/2967203 . It can produce lingerie, swimwear, topless and fully nude portraits of ONE adult woman. Every subject is a fictional, AI-generated adult (mid 20s); the prompt states her age and no real person is depicted. You are responsible for following Civitai's terms and the laws where you live. Do not use it to depict real people.

Pick a MODE, press Queue, get a finished 4:5 portrait. The workflow writes its own prompt: a built-in list of about 100 scene ideas per mode is expanded by Qwen3-VL 8B running inside ComfyUI into a detailed photographic paragraph, a clothing guard keeps every image inside the MODE you chose, and Qwen-Image 2.1 renders it. No LoRA is included or needed. Tested on an RTX 5080 16 GB.

⚡ Speed at a glance

• Default = max quality: 1792×2240, 25 steps, about 70 s per image on an RTX 5080 16 GB. The first run is slower while the 8B prompt expander loads; later runs reuse it.

• Faster: use the FAST switch in the CONTROL PANEL (v1.1) — 1 Fast (16 steps, no LoRA) renders in about 40 s, vs about 70 s at Quality (measured, RTX 5080, 32 test images) — about 1.7x quicker. For final images we still recommend Quality: in our test, Fast occasionally softened or doubled a limb/edge on 2 of 32 renders (both from the same MODE1 test seeds), an effect absent at Quality's 25 steps.

• Smaller images render faster too: set the Empty Latent Image size to 1280×1600 (about half the pixels of the default).

💻 Requirements — 12 GB+ (recommended 16 GB)

• GPU memory: 12 GB+ (recommended 16 GB). System RAM: 32 GB.

• What we measured: on a test build of this workflow (it had the optional Fix LoRA loaded; this release file does not load it), ComfyUI was started with --reserve-vram 4 to EMULATE a 12 GB card. Peak device memory was 13.2–14.2 GB and an image took 121–180 s. That was an emulation on a 16 GB card, not a physical 12 GB card, and the release workflow itself was not re-measured — we do not claim it needs less.

• 8 GB: expect it to be slow; we have not tested it. Below 8 GB: not tested.

• The speed figures elsewhere on this page (about 70 s and 40 s on an RTX 5080 16 GB) were measured on v1.1 and were not re-measured for v1.2.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

✨ Features

✅ One CONTROL PANEL, top-left — MODE, subject source, upscale switch, seed. Everything else is "Engine — no need to touch"

✅ 4 MODEs — 1 Dressed to Kill (fully dressed) · 2 Lace & Heat (lingerie / swimwear) · 3 Top Off (topless) · 4 Nothing But Skin (full nude). Clothing guards are built in

✅ Random from the built-in list, or "My own idea" — type your own scene line; the expander and guards still apply

✅ FAST switch (new in v1.1) — 0 Quality (25 steps, default, no LoRA) · 1 Fast (fewer steps, still no LoRA).

✅ BEAUTY switch (new in v1.1) — 0 Natural (default) · 1 Beauty (adds one line to the expander for a more polished, clearly adult look)

✅ Auto-prompt expander inside the graph — Qwen3-VL 8B (same file as the text encoder, no extra download)

✅ Hands-friendly prompt wording — simple hand anchors, no finger descriptions

✅ Optional Upscale — SeedVR2 2× (1792×2240 → 2560×3200), OFF by default

✅ Empty "Optional LoRA" slot — bypassed; drop in your own LoRA if you want one

✅ Civitai metadata embedded — model hash, prompt, seed, sampler in every PNG (Image Saver)

✅ No external files — all 4 subject lists are inside the workflow

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📦 Required Models (3 files, ≈17.3 GB)

• qwen_image_2.1_int8_convrot.safetensors (7.26 GB) — diffusion model → ComfyUI/models/diffusion_models/

• qwen3vl_8b_int8_convrot.safetensors (9.35 GB) — text encoder AND prompt expander → ComfyUI/models/text_encoders/

• qwen_image_2.1_vae_bf16.safetensors (0.68 GB) — VAE → ComfyUI/models/vae/

Optional upscale (only if you turn Upscale ON):

• seedvr2_ema_7b_fp16.safetensors (16.48 GB) + ema_vae_fp16.safetensors (0.50 GB) → ComfyUI/models/SEEDVR2/

• Lighter option: seedvr2_ema_3b_fp16.safetensors (6.78 GB) — in our 2-image check it matched the 7B on face and skin detail at 100% and ran at the same speed, a good choice if you have less RAM

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⬇️ Download Links (Hugging Face)

• https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/diffusion_models/qwen_image_2.1_int8_convrot.safetensors

• https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/text_encoders/qwen3vl_8b_int8_convrot.safetensors

• https://huggingface.co/Comfy-Org/Qwen-Image-2.1/resolve/main/vae/qwen_image_2.1_vae_bf16.safetensors

• SeedVR2 (optional): https://huggingface.co/numz/SeedVR2_comfyUI/tree/main

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🧩 Required Custom Nodes (all installable with ComfyUI-Manager)

1. WAS Node Suite — https://github.com/WASasquatch/was-node-suite-comfyui

2. ComfyUI-Impact-Pack — https://github.com/ltdrdata/ComfyUI-Impact-Pack

3. rgthree-comfy — https://github.com/rgthree/rgthree-comfy

4. ComfyUI_essentials — https://github.com/cubiq/ComfyUI_essentials

5. ComfyUI-Image-Saver — https://github.com/alexopus/ComfyUI-Image-Saver

6. ComfyUI-SeedVR2_VideoUpscaler (only for the optional Upscale) — https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler

Everything else is ComfyUI core. ComfyUI v0.37.0 or newer is required (Qwen-Image 2.1 nodes).

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🚀 How to Use

1. Download the 3 model files into the folders above. The loaders already use these exact file names.

2. In the CONTROL PANEL pick MODE: 1 Dressed to Kill · 2 Lace & Heat · 3 Top Off · 4 Nothing But Skin.

3. Press Queue. A new random image is made every run.

Optional:

• Subject source = 2 and type a scene in "My own idea" (for example: full body, red satin dress, rooftop bar at golden hour)

• Upscale: tick it in the switch on the left

• Several images: raise Batch count next to the Queue button

• Person box: the default is "Korean woman in her mid 20s" — change it to any adult woman you like

• FAST: 0 Quality (default) · 1 Fast (fewer steps, no download needed).

• BEAUTY: 0 Natural (default) · 1 Beauty — no extra download

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⚙️ Settings & Parameters

• Size: 1792×2240 (4:5 portrait) · Sampler: euler / simple · Steps: 25 · CFG: 1.0

• Seed: randomize each run (switch to "fixed" in the Seed node to repeat an image)

• Expander: Qwen3-VL 8B, temperature 0.7, max 768 tokens, plus 5 small clean-up steps (3 text clean-ups, a refusal / cut-off guard and a subject-clause trim)

• Output: PNG with Civitai metadata, saved to ComfyUI/output/qwen21_afterdark/<mode>/

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

💡 Performance Tips

• Base image 1792×2240: about 70 s on an RTX 5080 16 GB (first run is slower while models load). Upscale adds about 25 s.

• Upscale is OFF by default so first runs fit the 12 GB+ requirement above with 32 GB RAM. The 7B upscale model needs about 48 GB RAM; if you turn it on with less, use the 3B model.

• Pairs well with "Qwen Image 2.1 Fix v1.0" by _Envy_ (optional, not included, not needed): https://civarchive.com/models/2957332

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📋 Version History

• v1.0 — first release: 4-mode auto-prompt workflow, one control panel, no LoRA needed.

• v1.1 — adds two panel switches: FAST (0 Quality, 25 steps, no LoRA, about 70 s · 1 Fast, 16 steps, no LoRA, about 40 s) and BEAUTY (0 Natural · 1 Beauty, adds a polished-look line to the prompt, about 70 s, same cost as Quality). Resolution is 1792×2240 at every FAST level (1280×1600 is still available as a manual Empty Latent Image tip, see Performance Tips). Defaults unchanged (FAST=0, BEAUTY=0 render identically to v1.0). Tested on 16 cases x 2 seeds x 2 pages at 100% crop (32 Fast-arm renders, 16 Beauty-arm renders): 30/32 Fast renders (14/16 cases) were clean at 16 steps; 2/32 (both MODE1 test seeds) showed occasional ghosting/doubling on a limb or edge, an effect confirmed absent at Quality's 25 steps for the same seeds — use Quality if you need a guaranteed-clean result. Beauty read as more polished and clearly adult in all 16 cases.

• v1.2 — text-path update only; models, sampler, steps and the FAST / BEAUTY switches are unchanged. The built-in scene lists of MODEs 1, 3 and 4 now describe neutral, open poses (no kneeling, folded-arm or head-back lines); the MODE 2 (Lace & Heat) list is unchanged. One directional-light sentence was added to the prompt expander. A guard falls back to the raw scene line when the expander refuses or cuts off, and a clean-up step removes subject re-statements, skin-texture words and invented hand placements. The expander limit went from 400 to 768 tokens, skin wording in the prompts is positive-only (matte, dry, smooth, even), and hands are described only when the scene line does. The Optional LoRA slot is still empty and bypassed.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🔗 Cross-links

SFW version (dressed only, no lingerie or nudity): https://civarchive.com/models/2967203 — same engine and control panel. Follow my profile for more ComfyUI workflows.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⚠️ Known limitations (please read)

In our testing: outfits described as opaque or lined can render sheer or see-through, including a backless-gown opening that exposed the nipple in a mode meant to cover the chest; skin can look glossy or oily; a hand can land near the groin; eyes can come out closed. These are model-level behaviours and the prompt wording does not fully fix them — review every image before you post it and discard anything that is off.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📝 Notes & AI Disclosure

• All images are AI-generated with Qwen-Image 2.1 and show fictional adult women (mid 20s) — no real person is depicted.

• Adults only: keep the Person text an adult, and never edit the prompts or lists toward minors or real people.

• Clothing guards are prompt-based: check every image before you post it. Discard anything unclear, cropped or with wrong anatomy.

• Post nudity only where the platform allows it, and set the content rating correctly.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⭐ Found this useful?

• Like if it saved you time

• Comment your results — I read every one

• Follow for new ComfyUI workflows, all tested on 16 GB VRAM

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⚖️ Model Attribution & Licensing

Built with Qwen. Qwen-Image 2.1 by the Qwen team (Alibaba) — model files from Comfy-Org/Qwen-Image-2.1 on Hugging Face; please read the licence on that repository. Prompt expander: Qwen3-VL 8B (same repository).

• SeedVR2 (upscale): ByteDance-Seed, Apache-2.0; ComfyUI node by numz

• Node packs: WAS Node Suite (MIT), ComfyUI-Impact-Pack (GPL-3.0), rgthree-comfy (MIT), ComfyUI_essentials (MIT), ComfyUI-Image-Saver (MIT)

• Optional, not included: Qwen Image 2.1 Fix v1.0 by _Envy_ (Civitai)

Workflow JSON: CC0 Public Domain (free to reuse, no credit required).

🔗 Workflow by Thinni — feedback welcome!