Views
No views yet
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-qualityanime-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.
Compatible with versions 2509 and 2511.
pip install -U diffusers transformers accelerate1import torch
2from diffusers import DiffusionPipeline
3from diffusers.utils import load_image
4
5# switch to "mps" for apple devices
6pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2511", dtype=torch.bfloat16, device_map="cuda")
7pipe.load_lora_weights("prithivMLmods/Qwen-Image-Edit-2511-Anime")
8
9prompt = "Transform into anime."
10input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
11
12image = pipe(image=input_image, prompt=prompt).images[0]| Input Image | Edit Prompt | Output Image |
|---|---|---|
| Transform into anime. | ||
| Transform into anime. | ||
| Transform into anime. |
Transform into anime. to trigger the image generation.