---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
    url: images/output_1.png
  text: Anime, a girl with blue hair holding a sword
- output:
    url: images/output_6.png
  text: Anime, a samurai standing on a cliff during sunset
- output:
    url: images/output_8.png
  text: Anime, a wizard boy reading a floating book in a library
- output:
    url: images/output_10.png
  text: Anime, a fantasy castle surrounded by clouds and flying ships
base_model: Qwen/Qwen-Image
instance_prompt: Anime
license: apache-2.0
---
# Anime-Otaku-Qwen-Image

<Gallery />

## Model description 

# Anime-Otaku-Qwen-Image

**Anime-Otaku-Qwen-Image** is a LoRA fine-tuned adapter for the [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image) model, trained on the [Anime Gen v2 dataset](https://huggingface.co/datasets/xingjianleng/anime_gen_v2). It specializes in generating high-quality anime-style images.

---

## 🚀 Features

* Fine-tuned on **xingjianleng/anime_gen_v2** dataset.
* Generates **anime characters, scenes, and illustrations** in a consistent style.
* LoRA adapter (\~rank 16) — lightweight and easy to use with the base Qwen-Image model.
* Compatible with Hugging Face Diffusers pipelines.

---

## 🖌️ Usage

1. **Install dependencies** (if not installed):

```bash
pip install diffusers transformers accelerate safetensors torch
```

2. **Load base Qwen-Image and LoRA adapter**:

```python
from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "Qwen/Qwen-Image",
    torch_dtype=torch.bfloat16
).to("cuda")

# Load Anime-Otaku LoRA adapter
pipe.load_lora_weights("suayptalha/Anime-Otaku-Qwen-Image")

# Recommended prompt format
prompt = "Anime, a girl with blue hair holding a sword"

# Generate an anime image (1024x1024 recommended)
image = pipe(prompt, height=1024, width=1024, num_inference_steps=40, guidance_scale=7.5).images[0]

# Save output
image.save("output.png")
```

> Make sure your prompt starts with **"Anime, "** to match the training data format.

---

## ⚠️ Notes

* **Recommended inference resolution:** 1024×1024. You can reduce to 512×512 if GPU memory is limited.
* Use `torch_dtype=torch.bfloat16` or `torch.float16` for efficient VRAM usage.
* Enable attention slicing to reduce memory usage:

```python
pipe.enable_attention_slicing()
```

---

## Trigger words

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


## Download model


[Download](/suayptalha/Anime-Otaku-Qwen-Image/tree/main) them in the Files & versions tab.