wavespeed-ai/ghibli

Reimagine and transform your ordinary photos into enchanting Studio Ghibli style artwork

image-to-image

hot

preview
If enabled, the output will be encoded into a BASE64 string instead of a URL.
If set to true, the safety checker will be enabled.

Idle

https://d2g64w682n9w0w.cloudfront.net/media/images/1744805334134108357_5Ckigfed.jpg

Your request will cost $0.001 per image,
For $1 you can run this model approximately 1000 times.

README

wavespeed-ai/ghibli is an AI-powered tool that transforms user-uploaded photos into illustrations reminiscent of Studio Ghibli's iconic hand-drawn anime style. Developed using the EasyControl framework, this model applies Ghibli-style aesthetics while preserving the original facial features of the subjects.

Key Features

  • One-Click Ghibli Transformation: Easily convert your photos into charming, hand-drawn anime-style illustrations with a single upload.
  • Facial Feature Preservation: Maintains the unique facial characteristics of the original image while applying the Ghibli-style transformation
  • Commercial Use: Generated images can be used for personal and commercial purposes.
  • Open Source Friendly: The model is available for local deployment, allowing users to run it on their own devices without relying on external servers.

ComfyUI

wavespeed-ai/ghibli is also available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Limitations

  • Low-Resolution Output: Due to hardware constraints, the demo generates low-resolution images. For higher resolutions (1024+), setting up the model in a local environment is recommended.
  • Limited Training Data: The model was trained on a dataset of only 100 real Asian faces paired with GPT-4o-generated Ghibli-style counterparts, which may affect the diversity of outputs.​
  • Prompt Dependency: The quality and style of the generated images are highly dependent on the specificity and clarity of the input prompts.
  • Hardware Requirements for High-Resolution: Generating high-resolution images requires a suitable local setup with adequate computational resources.

Out-of-Scope Use

The model and its derivatives may not be used in any way that violates applicable national, federal, state, local, or international law or regulation, including but not limited to:

  • Exploiting, harming, or attempting to exploit or harm minors, including solicitation, creation, acquisition, or dissemination of child exploitative content.
  • Generating or disseminating verifiably false information with the intent to harm others.
  • Creating or distributing personal identifiable information that could be used to harm an individual.
  • Harassing, abusing, threatening, stalking, or bullying individuals or groups.
  • Producing non-consensual nudity or illegal pornographic content.
  • Making fully automated decisions that adversely affect an individual’s legal rights or create binding obligations.
  • Facilitating large-scale disinformation campaigns.

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.