Qwen-Image-Edit-2511-Anime
Qwen-Image-Edit-2511-Anime is an adapter (LoRA) developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model, specifically designed to convert input images into high-quality
anime-style flat cel shading. The adapter can be used in combination with the lighting model configured with 4 steps to produce high-resolution transformations with improved visual clarity and detail. A key strength of this model is its strong consistency during image translation, effectively preserving the original pose, subject proportions, viewing angle, and camera perspective of the input image while applying the anime aesthetic. This makes it suitable for use cases where structural accuracy and stylistic transformation are equally important. Below are some example outputs that demonstrate the model’s ability to deliver clean, consistent, and visually appealing anime-style results.
Quick Start with Diffusers
Compatible with versions 2509 and 2511.
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2511", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("prithivMLmods/Qwen-Image-Edit-2511-Anime")
prompt = "Transform into anime."
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]
Sample Inferences
| Input Image | Edit Prompt | Output Image |
|---|---|---|
| Transform into anime. | ||
| Transform into anime. | ||
| Transform into anime. |
Trained on ModelScope.cn
Trigger words
You should use Transform into anime. to trigger the image generation.
Download model
Download them in the Files & versions tab.