---
title: Lumatales-FL
canonical_url: "https://www.modelscope.cn/models/LiblibAI/Lumatales-FL"
md_url: "https://www.modelscope.cn/models/LiblibAI/Lumatales-FL.md"
repository: LiblibAI/Lumatales-FL
last_updated: 2025-02-17
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - black-forest-labs/FLUX.1-dev
base_model_relation: finetune
parameters: 153.2M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - diffusers
  - safetensors
frameworks:
  - pytorch
downloads: 855
stars: 1
tags:
  - text-to-image
  - stable-diffusion
  - diffusers
  - image-generation
  - flux
  - safetensors
---

# Lumatales-FL

> Lumatales-FL - LiblibAI 在 ModelScope 开源的模型。Lumatales-FL is finetuned on FLUX.1-dev, excels in cinematic lighting, atmosphere, composition, dramatic lighting, soft shadows, and a blend of retro and futuristic visual effects. Trained by JHAlchemy.

LiblibAI/Lumatales-FL 是 ModelScope 魔搭社区上的 153.2M 参数text-to-image-synthesis模型，采用 other 许可，基于 black-forest-labs/FLUX.1-dev 构建。

- **Repository**: LiblibAI/Lumatales-FL
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 153.2M
- **Base model**: black-forest-labs/FLUX.1-dev
- **Tags**: text-to-image, stable-diffusion, diffusers, image-generation, flux, safetensors
- **Downloads**: 855
- **Stars**: 1
- **Last updated**: 2025-02-17

Source: https://www.modelscope.cn/models/LiblibAI/Lumatales-FL

---

# Lumatales-FL

<div class="container">
  <img src="./poster.jpg" width="1024"/>
</div>

Lumatales-FL is finetuned on FLUX.1-dev, excels in cinematic lighting, atmosphere, composition, dramatic lighting, soft shadows, and a blend of retro and futuristic visual effects. Trained by [JHAlchemy](https://www.shakker.ai/userpage/bbe5dd5bb87d4daf9733b9ac27892ee4/publish).


<div class="container">
  <img src="./cover.png" width="1024"/>
</div>

## Comparison

The following example shows a simple comparison with FLUX.1-dev under the same parameter setting.

<div class="container">
  <img src="./compare.png" width="1024"/>
</div>

## Showcases
<Gallery />

## Inference

```python
import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/Lumatales-FL", weight_name="Lumatales.safetensors")
pipe.fuse_lora(lora_scale=0.9)
pipe.to("cuda")

trigger_word = "gushirensheng\(style\)"
prompt = trigger_word + ", A vast desert landscape with a rusty old car beside a road, surrounded by cacti. A young man in a striped shirt is standing next to a street sign, looking towards the horizon. The scene is brightly colored with vivid blues and oranges, giving it a surreal, quirky feel. The composition is wide and expansive, showing the barren landscape with dramatic rock formations in the background. The atmosphere feels nostalgic, empty, and isolated."

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
             width=800, height=1920,
            ).images[0]
image.save(f"example.png")
```

## Online Inference

You can also download this model at [Shakker AI](https://www.shakker.ai/modelinfo/baa0dc46adb34547860a17a571065c9d?from=feed), where we provide an online interface to generate images.


## Acknowledgements
This model is trained by our copyrighted users [JHAlchemy](https://www.shakker.ai/userpage/bbe5dd5bb87d4daf9733b9ac27892ee4/publish). We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) and the generated images are also non commercial.