---
title: FilmPortrait
canonical_url: "https://www.modelscope.cn/models/LiblibAI/FilmPortrait"
md_url: "https://www.modelscope.cn/models/LiblibAI/FilmPortrait.md"
repository: LiblibAI/FilmPortrait
last_updated: 2024-09-29
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: 306.3M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - diffusers
  - safetensors
frameworks:
  - pytorch
language:
  - en
downloads: 2107
stars: 1
tags:
  - text-to-image
  - stable-diffusion
  - diffusers
  - image-generation
  - flux
  - safetensors
---

# FilmPortrait

> FilmPortrait - LiblibAI 在 ModelScope 开源的模型。FilmPortrait is a LoRA model finetuned on FLUX.1-dev, specifically designed to enhance the film texture. It embodies a subdued, low-saturation color palette reminiscent of classic Japanese cinema, which is…

LiblibAI/FilmPortrait 是 ModelScope 魔搭社区上的 306.3M 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/FilmPortrait
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 306.3M
- **Base model**: black-forest-labs/FLUX.1-dev
- **Tags**: text-to-image, stable-diffusion, diffusers, image-generation, flux, safetensors
- **Downloads**: 2107
- **Stars**: 1
- **Last updated**: 2024-09-29

Source: https://www.modelscope.cn/models/LiblibAI/FilmPortrait

---

# FilmPortrait

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

FilmPortrait is a LoRA model finetuned on FLUX.1-dev, specifically designed to enhance the film texture. It embodies a subdued, low-saturation color palette reminiscent of classic Japanese cinema, which is particularly evident in its portrayal of characters (with a subtle bias towards Asian features), serene still lifes, and sweeping landscapes. The model delivers an exceptional aesthetic experience, capturing the essence of a bygone era with modern precision.

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


## Trigger words

You should use `filmfotos, film grain, reversal film photography` to trigger the image generation.


## 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/FilmPortrait', weight_name='filmfotos.safetensors')
pipe.fuse_lora(lora_scale=0.9)
pipe.to("cuda")

prompt = "a young girl, filmfotos, film grain, reversal film photography"

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
             width=768, height=1024,
            ).images[0]
image.save(f"example.png")
```

## Online Inference

You can also download this model at [Shakker AI](https://www.shakker.ai/modelinfo/ec983ff3497d46ea977dbfcd1d989f67?from=search), where we provide an online interface to generate images.


## Acknowledgements
This model is trained by our copyrighted users [DynamicWang](https://www.shakker.ai/userpage/dfca7abc67c04a9492ea738d864de070/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).