---
title: MGT-MOSS
canonical_url: "https://www.modelscope.ai/models/SAM-SANDY/MGT-MOSS"
md_url: "https://www.modelscope.ai/models/SAM-SANDY/MGT-MOSS.md"
repository: SAM-SANDY/MGT-MOSS
last_updated: 2026-11-04
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - openmoss/MOSS-Image-SFT
base_model_relation: adapter
parameters: 776.6M
tensor_type:
  - F16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: txt2img
downloads: 34
stars: 0
tags:
  - LoRA
  - text-to-image
---

# MGT-MOSS

> MGT-MOSS - An open-source model by SAM-SANDY on ModelScope. This model is trained using the Civision/model training environment and computing resources provided by ModelScope.

SAM-SANDY/MGT-MOSS is a 776.6M-parameter text-to-image-synthesis model on ModelScope. licensed under Apache License 2.0. derived from openmoss/MOSS-Image-SFT. and supports online inference (txt2img).

- **Repository**: SAM-SANDY/MGT-MOSS
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 776.6M
- **Base model**: openmoss/MOSS-Image-SFT
- **Online inference**: txt2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 34
- **Stars**: 0
- **Last updated**: 2026-11-04

Source: https://www.modelscope.ai/models/SAM-SANDY/MGT-MOSS

---

# 

## 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：100
* Total training steps：10000
* 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="SAM-SANDY/MGT-MOSS", origin_file_pattern="MGT-MOSS_c1-st10000.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")
```