---
title: flux-furry-lora
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/flux-furry-lora"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/flux-furry-lora.md"
repository: AI-ModelScope/flux-furry-lora
last_updated: 2024-08-12
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
parameters: 44.8M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 2253
stars: 2
tags:
  - LoRA
  - "Stable Diffusion"
  - image-generation
  - Flux
---

# flux-furry-lora

> flux-furry-lora - AI-ModelScope 在 ModelScope 开源的模型。This repository provides a checkpoint with trained LoRA for FLUX.1-dev model by Black Forest Labs

AI-ModelScope/flux-furry-lora 是 ModelScope 魔搭社区上的 44.8M 参数text-to-image-synthesis模型，采用 other 许可。

- **Repository**: AI-ModelScope/flux-furry-lora
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 44.8M
- **Tags**: LoRA, Stable Diffusion, image-generation, Flux
- **Downloads**: 2253
- **Stars**: 2
- **Last updated**: 2024-08-12

Source: https://www.modelscope.cn/models/AI-ModelScope/flux-furry-lora

---

This repository provides a checkpoint with trained LoRA for
[FLUX.1-dev model](https://huggingface.co/black-forest-labs/FLUX.1-dev) by Black Forest Labs
[<img src="https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/light/join-our-discord-rev1.png?raw=true">](https://discord.gg/FHY2guThfy)

![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/furry4.png?raw=true)

# Training details
[XLabs AI](https://github.com/XLabs-AI) team is happy to publish fune-tuning Flux scripts, including:

- **LoRA** 🔥
- **ControlNet** 🔥

[See our github](https://github.com/XLabs-AI/x-flux) for train script and train configs.

# Training Dataset
Dataset has the following format for the training process:

```
├── images/
│    ├── 1.png
│    ├── 1.json
│    ├── 2.png
│    ├── 2.json
│    ├── ...
```
A .json file contains "caption" field with a text prompt.

Thank https://civitai.com/user/dobrosketchkun and https://civitai.com/user/AlexV0iceh_DreamForge for datasets for loras

# Inference
## furry lora
```bash
python3 main.py \
 --prompt "Female furry Pixie with text 'hello world'" \
 --lora_repo_id XLabs-AI/flux-furry-lora --lora_name furry_lora.safetensors --device cuda --offload --use_lora \
 --model_type flux-dev-fp8 --width 1024 --height 1024 \
 --timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5 --guidance 4

```

![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/furry4.png?raw=true)
```bash
python3 main.py \
 --prompt "Female Orc with tribal face paint in fierce warrior armor, wielding a massive battle axe, standing in the midst of a battlefield, victorious warrior scene, elder scrolls, eslweyr, glitch aesthetic, anime-inspired, digital illustration, artstation, furry" \
 --lora_repo_id XLabs-AI/flux-furry-lora --lora_name furry_lora.safetensors --device cuda --offload --use_lora \
 --model_type flux-dev-fp8 --width 1024 --height 1024 \
 --timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5

```

![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/furry1.png?raw=true)

```bash
python3 main.py \
 --prompt "Male furry Lycanthrope with fur-covered body in ancient ruins, howling at the full moon, surrounded by eerie mist, werewolf transformation, elder scrolls, eslweyr, glitch aesthetic, anime-inspired, digital illustration, artstation, furry" \
 --lora_repo_id XLabs-AI/flux-furry-lora --lora_name furry_lora.safetensors --device cuda --offload --use_lora \
 --model_type flux-dev-fp8 --width 1024 --height 1024 \
 --timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5

```

![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/furry2.png?raw=true)

```bash
python3 main.py \
 --prompt "Female furry Pixie with iridescent wings in whimsical fairy attire, spreading pixie dust in a moonlit forest, mischievous sprite depiction, elder scrolls, eslweyr, glitch aesthetic, anime-inspired, digital illustration, artstation, furry" \
 --lora_repo_id XLabs-AI/flux-furry-lora --lora_name furry_lora.safetensors --device cuda --offload --use_lora \
 --model_type flux-dev-fp8 --width 1024 --height 1024 \
 --timestep_to_start_cfg 1 --num_steps 25 --true_gs 3.5

```

![Example Picture 1](https://github.com/XLabs-AI/x-flux/blob/main/assets/readme/examples/furry3.png?raw=true)

lora.safetensors falls under the [FLUX.1 [dev]](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) Non-Commercial License<br/>