Inkpunk-Diffusion on Hugging Face vs Drag Your GAN

Inkpunk-Diffusion is a Dreambooth-finetuned Stable Diffusion checkpoint on Hugging Face that renders bold ink-and-neon illustrations. Add the trigger token nvinkpunk to your prompt and you get a look influenced by Gorillaz, FLCL, and Yoji Shinkawa concept art. The weights ship under the CreativeML OpenRAIL-M license and run through the standard Diffusers text-to-image pipeline.

General-purpose SD checkpoints produce photorealistic output by default. Inkpunk-Diffusion narrows the aesthetic to stylized line work and saturated color palettes, which is why over 100 Hugging Face Spaces and community adapters build on top of it. You can load it locally with Diffusers, open the Gradio demo Space, or import into Draw Things and DiffusionBee without training your own LoRA.

The model card includes Colab and Kaggle notebooks plus sample images on the repo. Downloads hit roughly 400 per month with 988 community likes on the Hub. Inference Providers do not host it yet, so you run it on your own GPU, a local app, or a Hugging Face Space.

Drag Your GAN lets you reshape a generated image by dragging handle points to target spots on the canvas. Instead of training on labeled pose data or 3D priors, DragGAN moves pixels inside a pretrained GAN's image manifold so edits stay photorealistic even when occluded regions get hallucinated. The project page hosts the SIGGRAPH 2023 paper, demo clips, and links to open source code.

Most GAN editors rely on fixed training annotations or 3D meshes, which limits what you can deform. DragGAN pairs feature-based motion supervision with discriminative point tracking so handle points follow your cursor while staying on the object surface. That makes it useful for nudging animal poses, facial expressions, car angles, and landscape layouts without retraining the generator.

Researchers, graphics students, and computer vision engineers use it to prototype interactive image editing workflows. The Max Planck Institute page distributes the paper PDF and GitHub repo under a non-commercial Creative Commons license, with contact details for the lead author.