---
title: Canopus-LoRA-Flux-Anime
canonical_url: "https://www.modelscope.cn/models/prithivMLmods/Canopus-LoRA-Flux-Anime"
md_url: "https://www.modelscope.cn/models/prithivMLmods/Canopus-LoRA-Flux-Anime.md"
repository: prithivMLmods/Canopus-LoRA-Flux-Anime
last_updated: 2024-11-26
license: creativeml-openrail-m
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - black-forest-labs/FLUX.1-dev
base_model_relation: adapter
parameters: 306.3M
tensor_type:
  - F16
library_name:
  - pytorch
  - lora
  - diffusers
  - safetensors
frameworks:
  - pytorch
downloads: 1710
stars: 0
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - "template:sd-lora"
  - Flux
  - FluxDev
  - Anime
  - Euler
  - AdamW8bit
  - Realistic-Anime
---

# Canopus-LoRA-Flux-Anime

> Canopus-LoRA-Flux-Anime - prithivMLmods 在 ModelScope 开源的模型。Canopus-LoRA-Flux-Anime

prithivMLmods/Canopus-LoRA-Flux-Anime 是 ModelScope 魔搭社区上的 306.3M 参数text-to-image-synthesis模型，采用 creativeml-openrail-m 许可，基于 black-forest-labs/FLUX.1-dev 构建。

- **Repository**: prithivMLmods/Canopus-LoRA-Flux-Anime
- **License**: creativeml-openrail-m
- **Tasks**: text-to-image-synthesis
- **Parameters**: 306.3M
- **Base model**: black-forest-labs/FLUX.1-dev
- **Tags**: text-to-image, stable-diffusion, lora, diffusers, template:sd-lora, Flux, FluxDev, Anime, Euler, AdamW8bit, Realistic-Anime
- **Downloads**: 1710
- **Stars**: 0
- **Last updated**: 2024-11-26

Source: https://www.modelscope.cn/models/prithivMLmods/Canopus-LoRA-Flux-Anime

---

# Canopus-LoRA-Flux-Anime

<Gallery />

**The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.**

## Model description 

**prithivMLmods/Canopus-LoRA-Flux-Anime**

Image Processing Parameters 

| Parameter                 | Value  | Parameter                 | Value  |
|---------------------------|--------|---------------------------|--------|
| LR Scheduler              | constant | Noise Offset              | 0.03   |
| Optimizer                 | AdamW8bit | Multires Noise Discount   | 0.1    |
| Network Dim               | 64     | Multires Noise Iterations | 10     |
| Network Alpha             | 32     | Repeat & Steps           | 27 & 3.5K+ |
| Epoch                     | 17     | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English) 
    
    Total Images Used for Training : 220+ [ Hi-RES ] 

## Image Sources : Direct Links [i]

| Source Name     | URL                                                                | License                  |
|-----------------|--------------------------------------------------------------------|--------------------------|
| 4K Wallpapers   | [4kwallpapers](https://4kwallpapers.com/anime/)                    | Visit website for details|
| Pixabay         | [Pixabay](https://pixabay.com/images/search/anime%20wallpaper/)    | Free for commercial use  |
| Freepik         | [Freepik](https://www.freepik.com/free-photos-vectors/anime-wallpaper) | Free with attribution    |

Please make sure to follow the licensing terms of each source when using these images in your project.

🚀 **Scroll Down to the end for Sample Generations ⬇️.**

## Setting Up
```
import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "prithivMLmods/Canopus-Anime-Art-Flux-LoRA"
trigger_word = "Anime"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```
## Trigger prompts

    Anime ((masterpiece,best quality, detailed)), outdoor,wind_lift, souryuu asuka langley, interface headset, red bodysuit, (realistic:1.3)
    
    An anime girl in a blue dress and straw hat, with long black hair and flowing curly bangs, in the style of anime, against a background of a coastal street by the sea, on a bright sunny day, with flowers on a windowsill, with a cheerful expression, with detailed design, with a watercolor painting effect, and vibrant colors, Hayao Miyazaki's manga, with high resolution and clear details --ar 1:2 --stylize 750 --v 6.1
    
    Anime theme masterpiece,best quality,1girl,solo,looking at viewer, fur (clothing), black hair, black legwear,(electric guitar:1.4),  reflection, splash, droplets, rust, sparks, asphalt, ground vehicle, sports car, super car, mechanical,burning, playing instrument, livestream.

| Parameter       | Value                                                                                 |
|-----------------|---------------------------------------------------------------------------------------|
| Prompt          |  Anime ((masterpiece,best quality, detailed)), outdoor,wind_lift, souryuu asuka langley, interface headset, red bodysuit, (realistic:1.3) |
| Sampler         | euler                                                                                 |

## Trigger words

You should use `Anime` to trigger the image generation.

## Sample Generation Using Canopus-Anime-Art-Flux-LoRA 
## Image Gallery
| ![Image 1](assets/1.png) | ![Image 2](assets/2.png) | ![Image 3](assets/3.png) |
|--------------------------|--------------------------|--------------------------|
| ![Image 4](assets/4.png) | ![Image 5](assets/5.png) | ![Image 6](assets/6.png) |
| ![Image 7](images/5.png) | ![Image 8](images/8.png) | ![Image 9](images/9.png) |
| ![Image 10](images/4.png) | ![Image 11](images/7.png) | ![Image 12](images/6.png) |


## App File Structure

/project-root/

├── .gitattributes         
├── README.md      
├── app.py             
├── pythonproject.py     

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Canopus-Anime-Art-FluxDev-LoRA/tree/main) them in the Files & versions tab.

.

.🤗: https://hf.co/prithivmlmods