MOSS-Image Panel Workflow (NSFW) — one ComfyUI panel, four coverage modes, optional free-prompt box.

For AI-created adult characters only. Every person in the example images is an AI-generated adult woman ("adult woman in her early 20s" is written into every preset). Never use this workflow on photos of real people, and do not use it to remove clothes from anyone's picture. There is no image input in this graph.

Pick a MODE, press Queue. Prompt templates, the adult wording, file names and the output folder are built in. Everything you touch is in the group called CONTROL PANEL.

🎚️ The 4 modes, same panel, same seed family

Mode 1 · Glamour (dressed)

Mode 2 · Suggestive

Mode 3 · Topless (bottoms on)

Mode 4 · Full nude

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🧾 What I tested (RTX 16 GB, ComfyUI 0.44)
• All four modes ran through this exact file: 2:3 images (1184×1776) in 85–105 s each, peak VRAM 14.0 GB, no errors. The example images on this page were made with this file; each PNG contains the prompt, the seed and the workflow, so you can drag it into ComfyUI.
• The result is deterministic: same seed and same panel state give the same pixels (checked on all runs).
• SeedVR2 upscale is OFF by default. In my one SeedVR2 test the system RAM reached 99 % on a 64 GB PC with other programs open. Turn it on only when you have a lot of free RAM.
• Tested on one 16 GB card only. Hands and small details can still be wrong; try another seed.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⚡ Quick start
1) Download the file. It is only the graph, no model weights.
2) Put the model files in the usual ComfyUI folders (names below), install the custom nodes, restart ComfyUI, open the workflow.
3) In CONTROL PANEL set MODE (and SEED), leave FREE at 0, Queue. One Queue = one image.
4) Images are saved to ComfyUI/output/MOSS_Image_NSFW/ as moss_nsfw_(time).png.

🎛️ The panel
• MODE: 1 Glamour (dressed) · 2 Suggestive (lingerie / swimwear) · 3 Topless (bottoms on) · 4 Full nude. The mode text states the coverage and "adult woman in her early 20s". Each mode picks one scene line at random from its own template; the four templates are inside the graph as plain text boxes you can edit
• SEED: fixed or random
• FINISH: 0 = raw (default) · 1 = SeedVR2 upscale (RAM heavy)
• extra words: text added to the preset. Keep the adult wording
• FREE = 1: your own prompt in the FREE PROMPT box (no preset). STYLE = 1 adds a short "photorealistic quality" phrase. FREE SIZE: 1 = 2:3 · 2 = 1:1 · 3 = 3:2. STEPS 50 and CFG 3 are the MOSS defaults. Free mode is your own prompt: it must follow the site rules and the model licenses, and the person must be an adult, AI-created character━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📦 Required models (this page does not host them)
• UNet: moss_image_sft_int8_convrot.safetensors (5.4 GB) → models/diffusion_models
• Text encoder: qwen3.5_9b_int8_convrot.safetensors (9.8 GB), loader type "moss_image" → models/text_encoders
• VAE: flux2-vae.safetensors → models/vae
• Optional upscale: SeedVR2 7B (seedvr2_ema_7b_fp16.safetensors) + ema_vae_fp16.safetensors
Pick the files in the loader nodes if your file names differ.

🧩 Required custom nodes
ComfyUI-Impact-Pack · was-node-suite-comfyui · ComfyUI-Custom-Scripts (pysssss) · comfyui_essentials · ComfyUI-Easy-Use · comfyui_layerstyle (Seed node) · ComfyUI-Image-Saver · rgthree-comfy (the SeedVR2 on/off switch) · ComfyUI-SeedVR2_VideoUpscaler (only for FINISH = 1)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

⚙️ Settings used
50 steps · Euler / sgm_uniform · CFG 3 · model shift 5 · skip-layer guidance on layer 22. Prompts and seeds are saved in every PNG.

💡 Tips
• Keep FINISH at 0 while you explore.
• Mode 3 keeps the bottoms on; if a result shows more than the mode says, change the seed.
• Open the workflow from the ComfyUI workflow list or drag in one of the example PNGs.

⚠️ Limits
• Adult content. AI-created adult characters only. No real people, no celebrities, no photo input.
• The model sometimes ignores a coverage word; check every image before you post it.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📝 AI disclosure
Every example image on this page is AI-generated with this workflow.

⚖️ Licenses and credits
• MOSS-Image (SFT) by OpenMOSS: Apache-2.0 according to the model card.
• Qwen3.5-9B text encoder: Apache-2.0 on its Hugging Face card (huggingface.co/Qwen/Qwen3.5-9B).
• FLUX.2 VAE: two sources say different things, so read them yourself before you use it. The BFL GitHub README (github.com/black-forest-labs/flux2) says the FLUX.2 autoencoder is released under Apache 2.0 and links the file ae.safetensors in the FLUX.2-dev repository on Hugging Face. That repository (huggingface.co/black-forest-labs/FLUX.2-dev) is labeled FLUX Non-Commercial License. I make no claim about commercial use of the VAE, and I do not forbid it either. This page shares only the workflow graph, not the VAE.
• SeedVR2 by ByteDance (optional upscale): follow its license.
• The workflow graph itself is free to use.

⭐ If it saved you time, a like or a comment with your result helps others find it.