Real-looking hands for MOSS Image. Natural fingers, believable nails and manicures, rings that sit right, and hands that actually hold things: phones, cups, keys, drinks. It also takes the glossy "AI" edge off skin, so it fits realistic and influencer-style shots.Made by the SeedraAI team. We build AI influencer content every day, and this is one of the tools from our own pipeline.

Natural Hands | MOSS | by SeedraAI

First release. Trigger: h4nds, weight 0.8. More tools and workflows in the SeedraAI Discord: <a target="_blank" rel="ugc" href="https://discord.com/invite/seedraai">https://discord.com/invite/seedraai</a>

hands_moss_v1.safetensors

v1.0


# 

## Model Introduction

This model is trained using the [Civision/model training](https://modelscope.ai/civision/modelTraining) environment and computing resources provided by ModelScope.

* Model Type: LoRA
* Base Model: [openmoss/MOSS-Image-SFT](https://modelscope.ai/models/openmoss/MOSS-Image-SFT)
* Training Code: [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)
* Data amount：88
* Total training steps：4000
* License: Apache-2.0

## Inference Code

Install [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio):

```bash
pip install diffsynth
```

Inference:

```python
from diffsynth.pipelines.moss_image import MOSSImagePipeline, ModelConfig
import torch

pipe = MOSSImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="text_encoder/model*.safetensors"),
        ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", computation_dtype=torch.float32),
    ],
    tokenizer_config=ModelConfig(model_id="openmoss/MOSS-Image-SFT", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="cfgscale/hands_moss_v1", origin_file_pattern="hands_moss_v1_c1-st4000.safetensors"))

prompt = "a cat"
image = pipe(prompt, height=1024, width=1024, seed=0, num_inference_steps=50, cfg_scale=3.0)
image.save("image.jpg")
```


Files with SHA256: 8554752a108f7a7c1b6a113a0753bc9009236f9dee8f13baea9f06e11eaedc18