MOSS-Image Beauty LoRA GGUF

Separate F16 GGUF conversion of the portrait and beauty-photography LoRA from axiomofmind/Moss-image-beauty-lora. It is designed to be applied at inference time to axiomofmind/Moss-Image-SFT-GGUF, keeping the adapter strength adjustable without creating a merged model for each base quantization or scale.

The adapter emphasizes polished close portraits, softly directed light, detailed skin and hair, restrained backgrounds, and editorial beauty photography. This repository contains the LoRA adapter only. It does not contain the base diffusion transformer, Qwen3.5 text encoder, tokenizer, or VAE.

File

The adapter uses rank 16 and alpha 16. Its trigger phrase is moss_beauty_style; place it at the beginning of the prompt. Scale 1.0 produced the preferred balance during local evaluation; scales 0.7, 0.8, and 0.9 also performed well.

Required components

• A compatible base transformer from Moss-Image-SFT-GGUF. Q8_0 was validated; Q4_K_S uses the same MOSS architecture and LoRA targets.
• A MOSS-enabled stable-diffusion.cpp build.
• A Qwen3.5-9B text encoder, the official MOSS tokenizer.json, and the official MOSS / FLUX.2 VAE. See the base GGUF repository for links and setup notes.

Usage

Put the base GGUF and this LoRA GGUF in accessible locations. The <lora:...> tag selects the adapter file and scale; moss_beauty_style is the learned trigger sent to the text encoder.

sd-cli.exe `
  --diffusion-model MOSS-Image-SFT-Q8_0.gguf `
  --llm text_encoder/model.safetensors.index.json `
  --vae vae/diffusion_pytorch_model.safetensors `
  --tokenizer tokenizer/tokenizer.json `
  --lora-model-dir . `
  --lora-apply-mode at_runtime `
  --cfg-scale 3 `
  --steps 30 `
  --sampling-method euler `
  --scheduler discrete `
  --flow-shift 5 `
  --seed 42 `
  --rng cpu `
  --sampler-rng cpu `
  -W 1024 -H 1024 `
  -p "moss_beauty_style, a close portrait of a young woman with dark brown skin and freckles, her dark hair framing her face as she gazes forward with light brown eyes and neutral expression, wearing a black garment with soft directional light highlighting her skin and lips. <lora:MOSS-Image-Beauty-LoRA-F16:1.0>" `
  -o beauty-gguf.png

Quantized transformers automatically select runtime LoRA application. --lora-apply-mode at_runtime is explicit here because it is the validated path. Ready-to-edit PowerShell and Bash wrappers are provided under examples/.

Controlled validation

The adapter was tested with MOSS-Image-SFT-Q8_0.gguf. Every comparison row below used the same description in both columns, along with the same base model, text encoder, VAE, 1024×1024 resolution, 30 steps, CFG 3, Euler/discrete sampling, flow shift 5, and seed 42.

• The stock prompt omitted both the trigger phrase and LoRA tag.
• The adapter prompt added moss_beauty_style and <lora:MOSS-Image-Beauty-LoRA-F16:1.0>.
• stable-diffusion.cpp reported all 504 / 504 LoRA tensors applied.
• The results visually reproduced the same controlled stock-versus-adapter behavior shown by the safetensors reference images in the source repository.

Prompts, shown without the moss_beauty_style prefix and <lora:MOSS-Image-Beauty-LoRA-F16:1.0> suffix used only in the LoRA column:

1. a close portrait of a young woman with dark brown skin and freckles, her dark hair framing her face as she gazes forward with light brown eyes and neutral expression, wearing a black garment with soft directional light highlighting her skin and lips.
2. a young woman with fair skin and freckles wears a black turtleneck, her dark hair pulled back with loose strands framing her face, as she gazes directly at the camera with a neutral expression under soft, even studio lighting against a plain gray background.
3. a young woman with fair skin and dark brown hair parted in the middle, her bangs framing a direct gaze with light blue eyes and subtle freckles, wears a black velvet coat with a high collar, her lips neutral and skin softly lit against a blurred neutral background.
4. a young woman with warm brown skin and dark brown hair styled in a loose updo with soft tendrils framing her face, wearing subtle makeup with defined brows, brown eyes, and a nude lip, posed in a close-up against a plain white background with soft directional lighting highlighting her natural skin texture.

Timings were measured on an NVIDIA RTX PRO 6000 Blackwell Max-Q and are correctness checks, not general performance benchmarks.

Conversion

Converted independently from pytorch_lora_weights.safetensors using stable-diffusion.cpp commit b13a482:

sd-cli.exe -M convert `
  -m pytorch_lora_weights.safetensors `
  -o MOSS-Image-Beauty-LoRA-F16.gguf `
  --type f16 `
  --convert-name `
  -t 16

The source adapter was trained against MOSS-Image-Base, and the published weights are the selected 2,000-step checkpoint. Its transformer targets are compatible with MOSS-Image-SFT, which produced the preferred evaluation results. See conversion.json for machine-readable conversion and validation metadata.

Intended use and limitations

This adapter is intended for creative adult portrait, editorial, fashion, and beauty-photography generation. Its training set contains 176 captioned images and is portrait-dominant, adult-only, and female-form-only. It may generalize less reliably to children, men, groups, full-body scenes, landscapes, objects, text, or non-photographic styles. Generated people are synthetic and should not be represented as real individuals. The adapter can reproduce demographic and aesthetic biases present in its training data and underlying model.

License

The adapter and this conversion are provided under Apache License 2.0, matching the source release and base model. This is an independent community conversion and is not affiliated with or endorsed by OpenMOSS.