Moss Image NSFW Uncensored LoRA

An adult photographic-content LoRA for MOSS-Image-SFT or MOSS-Image-Base, with MOSS-Image-SFT preferred for inference. It is tuned for explicit adult portraiture, nude poses, indoor scenes, and close photographic compositions.

A GGUF conversion (44% less VRAM on Q8 and 66% less VRAM on Q4) is also available here: https://huggingface.co/axiomofmind/Moss-image-nsfw-uncensored-lora-GGUF which can be used with MOSS-Image-SFT-GGUF

Adult-content notice: This repository contains explicit sexual imagery and prompts depicting adults. It is intended only for adults in jurisdictions where such content is lawful. Do not use it to depict minors or age-ambiguous subjects, sexual abuse, non-consensual acts, exploitation, or sexualized representations of real people without their explicit consent.

Bundled merged model (scale 0.7)

For convenience, merged-model/ contains a complete standalone Diffusers model with this LoRA fused into OpenMOSS-Team/MOSS-Image-SFT at the preferred evaluated scale of 0.7. It was reloaded and validated at 1024 x 1024 without a separate adapter. The merged model has a fixed strength and is about 25.4 GiB; users who want a smaller download or adjustable strength should use the LoRA files at the repository root.

The merged model still expects the moss_xvstyle trigger phrase at the beginning of the prompt. Download only the merged bundle with:

hf download axiomofmind/Moss-image-nsfw-uncensored-lora \
  --include "merged-model/**" \
  --local-dir ./Moss-image-nsfw-uncensored-lora

Then load ./Moss-image-nsfw-uncensored-lora/merged-model as the local model path with the MOSS custom Diffusers pipeline. No LoRA path or runtime LoRA scale is needed.

Merge at a different strength

The included scripts/merge_moss_lora.py utility can create another standalone model from the original SFT model and the root adapter files. For example, to bake scale 1.0:

hf download OpenMOSS-Team/MOSS-Image-SFT --local-dir ./MOSS-Image-SFT
hf download axiomofmind/Moss-image-nsfw-uncensored-lora \
  adapter_config.json pytorch_lora_weights.safetensors scripts/merge_moss_lora.py \
  --local-dir ./Moss-image-nsfw-uncensored-lora

python ./Moss-image-nsfw-uncensored-lora/scripts/merge_moss_lora.py \
  --model-path ./MOSS-Image-SFT \
  --lora-path ./Moss-image-nsfw-uncensored-lora \
  --output ./Moss-image-nsfw-uncensored-merged-s1p0 \
  --scale 1.0 \
  --device cuda:0 \
  --preferred-trigger moss_xvstyle

Use a new output directory for each strength. After merging, the chosen scale is permanent; continue using moss_xvstyle in prompts.

ComfyUI compatibility

The root pytorch_lora_weights.safetensors uses Diffusers / PEFT keys such as transformer.layers.0.proj.q.lora_A.weight. ComfyUI's native MOSS-Image loader addresses the same modules under diffusion_model.layers..., so loading the root file directly can report lora key not loaded.

Use the native ComfyUI variant instead:

1. Update ComfyUI to a version with native MOSS-Image support; commit b1a247c or newer contains the required loader code.
2. Put MOSS-Image-NSFW-Uncensored-LoRA-ComfyUI.safetensors in ComfyUI/models/loras/.
3. Use ComfyUI's standard LoRA loader with model strength 0.7 and clip strength 0.0.
4. Begin the prompt with moss_xvstyle.

Download only this variant with:

hf download axiomofmind/Moss-image-nsfw-uncensored-lora \
  MOSS-Image-NSFW-Uncensored-LoRA-ComfyUI.safetensors \
  --local-dir ./ComfyUI/models/loras

The conversion is namespace-only: transformer. becomes diffusion_model.. Tensor values, shapes, dtypes, rank, and alpha behavior are unchanged. All 504 converted tensors were checked against the 252 corresponding MOSS-Image-SFT modules. The reproducible converter is scripts/convert_moss_lora_for_comfyui.py.

The separate GGUF adapter is for stable-diffusion.cpp and is not this native ComfyUI format. The bundled merged-model/ avoids runtime LoRA key matching when used as a Diffusers model, but the sharded Diffusers directory is not a direct replacement for the native ComfyUI LoRA file in a standard ComfyUI model-loading workflow.

Recommended settings

• Trigger: moss_xvstyle
• Preferred underlying model: OpenMOSS-Team/MOSS-Image-SFT
• Also compatible with: OpenMOSS-Team/MOSS-Image-Base
• Selected checkpoint: 2,000 steps
• LoRA scale: 0.7
• Inference steps: 30
• Guidance scale: 3.0
• Resolution: 1024 x 1024
• Negative prompt: empty

Place moss_xvstyle at the beginning of the prompt. The adapter was trained against MOSS-Image-Base, which remains the training parent recorded in adapter_config.json. Its transformer targets are compatible with MOSS-Image-SFT, and SFT + LoRA at scale 0.7 produced the preferred local evaluation results.

Examples

All featured examples use MOSS-Image-SFT plus this exact 2,000-step adapter at scale 0.7, image seed 42, 30 inference steps, guidance scale 3.0, and 1024 x 1024 resolution.

Sample 0 — rear close-up

Prompt: moss_xvstyle, a close-up photograph of an adult woman with fair skin and long blonde hair, viewed from behind as she bends forward over a gray surface. Her body is positioned with her buttocks prominently displayed, revealing her vulva and labia in a natural, unposed state. She wears a white thong that is pulled down to expose her intimate area. The lighting is soft and natural, highlighting the smooth texture of her skin. The background is blurred, suggesting an indoor setting with neutral tones.

Sample 1 — bedroom mirror scene

Prompt: moss_xvstyle, A full-body photograph shows an adult woman with a curvaceous body and long brown hair styled in a braid, kneeling on a wooden floor with her back to the camera and her head resting on her arms. Her skin tone is light tan, and she is completely nude, with her large buttocks prominently displayed and her vulva visible between her thighs. She wears a gold anklet and a green floral hair accessory. Her gaze is directed downward, and her expression is neutral. The setting is a bedroom with a large mirror reflecting her pose, a white upholstered chair, and light-colored curtains. The lighting is soft and indoor, and the camera angle is a medium shot from behind.

Sample 2 — mirror selfie

Prompt: moss_xvstyle, A close-up photograph shows an adult woman with light brown wavy hair lying face down on a light-colored surface, holding a dark blue smartphone with a triple-lens camera system to take a mirror selfie. Her pale skin is visible on her rounded buttocks and thighs, and she is completely nude, with her vulva and labia clearly exposed between her spread legs. The setting appears to be a bathroom with a plain white wall and a partial view of kitchen appliances in the background. The lighting is soft and even, and the camera angle is from behind and slightly above, focusing on her lower back and genital area.

Sample 3 — crouching room portrait

Prompt: moss_xvstyle, a nude adult woman with fair skin and shoulder-length light brown hair is photographed in a medium close-up from a slightly low angle. She is crouching with her legs spread wide, exposing her vulva and labia, while her left hand rests on a wooden surface behind her. Her right arm is raised above her head. She has a belly button piercing with a silver stud and is wearing white ankle socks with yellow smiley faces. Her facial expression is neutral, and she gazes directly at the camera. The setting is an indoor room with a white wall, a dark television screen, and a white lamp in the background. The lighting is soft and even, highlighting her smooth skin and large breasts. The image is a photograph.

Sample 4 — red-top rear pose

Prompt: moss_xvstyle, A medium close-up photograph from behind and slightly to the side of an adult woman with long blonde hair featuring darker roots, wearing a red strap top with a silver buckle visible on her upper back. She is bent forward over a wooden surface, her pale skin and large buttocks prominently displayed. Her vulva and labia are clearly visible between her thighs as she leans forward, with her right hand partially visible near her lower back. The setting is an indoor room with a beige couch and light-colored wall in the background, illuminated by soft, even indoor lighting.

Sample 5 — plaid-skirt pose

Prompt: moss_xvstyle, A medium close-up photograph of an adult woman with long wavy blonde hair and fair skin, smiling and looking toward the camera while bending forward. She wears a white tank top and a blue plaid skirt lifted to expose her buttocks, vulva, and labia, with beige lace panties pulled down and beige thigh-high stockings. Her left hand grips the panty waistband near her crotch, and her right hand rests on her hip. Visible tattoos include a winged figure on her upper left arm, a heart on her left forearm, and a cherub on her left thigh. The setting is an indoor room with a white tablecloth-covered table, a wooden chair, a hexagonal mirror, and white curtains in the background. Bright, even indoor lighting illuminates the scene from a frontal camera angle.

Sample 6 — reclining POV

Prompt: moss_xvstyle, an adult woman with long blonde hair styled in loose waves and fair skin is positioned in a close-up POV shot, lying on her back with her legs spread wide to expose her vulva and labia. She wears a black halter-style top that leaves her breasts bare and has a tattoo on her lower abdomen. Her right hand rests between her thighs with fingers near her clitoris, and she wears a ring on her finger. Her mouth is slightly open and she gazes directly at the camera with an aroused expression. The setting appears to be a modern indoor room with light-colored walls, a metal railing, and wooden cabinetry in the background, illuminated by soft overhead lighting. The image is a photograph.

Sample 7 — side-lying close-up

Prompt: moss_xvstyle, A close-up photograph of an adult woman lying on her side on a gray fabric surface, her left hand resting on her upper thigh with pink-painted fingernails visible. She has light brown skin and is nude, with her legs bent and pressed together, exposing her vulva and inner thighs. Her gaze is directed toward the camera with a neutral expression. The background is softly blurred, suggesting an indoor setting with natural lighting. The image is a photograph.

Base, SFT, and LoRA comparison

The table compares three generation conditions using the same descriptive prompt, image seed 42, 1024 x 1024 resolution, 30 inference steps, and guidance scale 3.0:

• MOSS-Image-Base + LoRA: the original training parent with this adapter at scale 0.7 and moss_xvstyle in the prompt.
• Stock MOSS-Image-SFT: SFT without the LoRA and with only the trigger phrase removed.
• MOSS-Image-SFT + LoRA: the preferred inference configuration, with this adapter at scale 0.7 and the trigger included.

Use with Diffusers and PEFT

MOSS-Image uses a custom Diffusers pipeline. Attach the adapter to its transformer with PEFT:

import json

import torch
from diffusers import DiffusionPipeline
from huggingface_hub import hf_hub_download
from peft import LoraConfig, inject_adapter_in_model, set_peft_model_state_dict
from peft.tuners.lora.layer import LoraLayer
from safetensors.torch import load_file

repo_id = "axiomofmind/Moss-image-nsfw-uncensored-lora"
base_model = "OpenMOSS-Team/MOSS-Image-SFT"  # Preferred; Base is also supported.
lora_scale = 0.7

config_path = hf_hub_download(repo_id, "adapter_config.json")
weights_path = hf_hub_download(repo_id, "pytorch_lora_weights.safetensors")

with open(config_path, encoding="utf-8") as file:
    config = json.load(file)

pipe = DiffusionPipeline.from_pretrained(
    base_model,
    custom_pipeline="pipeline_moss_image",
    trust_remote_code=True,
    torch_dtype={"default": torch.bfloat16, "vae": torch.float32},
)
pipe.scheduler = type(pipe.scheduler).from_config(pipe.scheduler.config)

inject_adapter_in_model(
    LoraConfig(
        r=config["r"],
        lora_alpha=config["lora_alpha"],
        target_modules=config["target_modules"],
    ),
    pipe.transformer,
)

state = {
    key.removeprefix("transformer."): value
    for key, value in load_file(weights_path, device="cpu").items()
}
_, unexpected = set_peft_model_state_dict(pipe.transformer, state)
if unexpected:
    raise RuntimeError(f"Unexpected LoRA tensors: {unexpected[:5]}")

for layer in pipe.transformer.modules():
    if isinstance(layer, LoraLayer):
        layer.set_scale("default", lora_scale)

pipe.transformer.to(torch.bfloat16)
pipe.to("cuda")

prompt = (
    "moss_xvstyle, an explicit photograph of an adult woman in a softly lit "
    "bedroom, natural skin texture, close composition."
)

image = pipe(
    prompt,
    negative_prompt="",
    width=1024,
    height=1024,
    num_inference_steps=30,
    guidance_scale=3.0,
    uncond_skip_layers=[22],
    generator=torch.Generator("cpu").manual_seed(42),
).images[0]

image.save("moss_xvstyle.png")

Training details

• Training base model: OpenMOSS-Team/MOSS-Image-Base
• Preferred inference model: OpenMOSS-Team/MOSS-Image-SFT
• Selected checkpoint: 2,000 steps
• Training images: 221
• Resolution: 1024
• LoRA rank / alpha: 16 / 16
• Target modules: transformer attention projections and feed-forward projections
• Optimizer: AdamW
• Learning rate: 1e-4
• Scheduler: constant with warmup
• Batch size / gradient accumulation: 1 / 1
• Weight decay: 0.01
• Training seed: 42
• Caption dropout: 0
• Random horizontal flip: disabled
• Training environment: local hardware

Intended use, restrictions, and limitations

This adapter is intended for lawful creative generation involving clearly adult fictional subjects. Users are responsible for complying with applicable law, platform rules, privacy rights, and consent requirements.

Do not use this adapter for:

• Any depiction of minors or age-ambiguous people in sexual contexts.
• Sexual abuse, exploitation, coercion, trafficking, or non-consensual imagery.
• Sexualized deepfakes or depictions of identifiable real people without explicit consent.
• Harassment, blackmail, doxxing, or attempts to evade legal or platform safeguards.

The model can produce anatomical errors, malformed hands, inconsistent reflections, implausible poses, or outputs that diverge from the prompt. A trigger word does not guarantee a particular style or content level. Review outputs before use or distribution.

License

The adapter files are provided under the Apache License 2.0, matching the base model. This is an independent community LoRA and is not an official OpenMOSS release. The license does not override laws or third-party rights governing generated or source content.