---
title: mgwr-M87
canonical_url: "https://www.modelscope.cn/models/hf/mgwr-M87"
md_url: "https://www.modelscope.cn/models/hf/mgwr-M87.md"
repository: hf/mgwr-M87
last_updated: 2026-08-14
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - krea/Krea-2-Turbo
base_model_relation: adapter
parameters: 114.3M
tensor_type:
  - BF16
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 295
stars: 75
tags:
  - text-to-image
  - lora
  - diffusers
  - "template:diffusion-lora"
---

# mgwr-M87

> mgwr-M87 - hf 在 ModelScope 开源的模型。M87 (early-preview) v1

hf/mgwr-M87 是 ModelScope 魔搭社区上的 114.3M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 krea/Krea-2-Turbo 构建，并支持在线推理（txt2img）。

- **Repository**: hf/mgwr-M87
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 114.3M
- **Base model**: krea/Krea-2-Turbo
- **Online inference**: txt2img
- **Tags**: text-to-image, lora, diffusers, template:diffusion-lora
- **Downloads**: 295
- **Stars**: 75
- **Last updated**: 2026-08-14

Source: https://www.modelscope.cn/models/hf/mgwr-M87

---

# M87 (early-preview) v1

<Gallery />

## Model description 

M87 is an early-preview aesthetic LoRA for KREA-2 Turbo, built to make the model feel more creative, cinematic, and visually refined.

It focuses on improving the overall look and feel of generations: stronger compositions, richer lighting, softer atmosphere, better visual texture, and a more polished image language.

Trained on a curated 100-image aesthetic dataset, M87 works as a visual enhancement layer for KREA-2 Turbo, helping outputs feel more art-directed without locking the model into one specific subject or style.

## Trigger words

You should use `--preview` to trigger the image generation.


## Download model


[Download](/mgwr/M87/tree/main) them in the Files & versions tab.