<h3 id="moss-a-new-version-of-alise-reworked.">MOSS A new version of Alise, reworked.</h3><span style="background-color:rgb(31, 32, 35);color:rgb(140, 143, 163);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:14px">Usage Tips 0.8-1Alisa is a versatile, character LoRA1. Street Cafe (Casual):&gt; <code>candid medium portrait of a woman sitting at an outdoor french cafe, resting chin on hand, looking at camera, soft morning sunlight, wearing black ribbed t-shirt, 50mm lens, shallow depth of field, raw photo</code>2. Direct Flash (Atmospheric):&gt; <code>raw on-camera flash photography, full portrait of a woman, direct harsh flash, hard shadow behind, messy dark hair, authentic skin texture, wearing black long-sleeve top, 35mm snapshot</code>3. Outdoor Golden Hour (Sporty):&gt; <code>candid waist-up portrait of a woman in nature, hair tied back in a messy ponytail, wearing grey tank top, warm afternoon sunlight, detailed skin texture, 85mm portrait photography</code>

Alisa  —  LoRA | MOSS / Krea 2 /

Alisav1m.safetensors

v1.0 MOSS

v1.0 Krea 2


# 

## 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：22
* Total training steps：2000
* 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="bazya75/Alisa", origin_file_pattern="Alisa_c1-st2000.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: c52ed972748f759294d4efe96d293dde479a7aa164fa9485bfa1ca86b0b6c56a