Atlas KREA Stable Diffusion creates or edits images with generative AI and text-based controls.
A blog post by Justin Pinkney explaining how to toonify yourself, making a photo-realistic cartoon model using StyleGAN model blending. It describes transfer learning by fine-tuning a faces model on animated film characters, then swapping layers so low resolution layers give a cartoon face structure while high resolution layers keep photo-realistic rendering.
Magic Eraser is a web tool from Magic Studio that removes objects, people, text, blemishes and patterns from photos. Users upload an image, select the area with a brush, erase with AI and download the result. The source states unlimited free use with no signup, and lists uses such as real estate, photography, fashion, e-commerce and social media.
IOPaint is a free, open-source and fully self-hostable image inpainting and outpainting tool powered by AI models. It can erase unwanted objects, add or replace elements in images, generate text, and generate new pixels around images to enlarge them, with various models available for different tasks.
Polarr offers web and mobile photo and video filters and editing tools. The page lists a Pro editor for iOS, Mac, Windows and web, a beta batch RAW editing AI workflow in the browser called Polarr Next, and 24FPS video effects for iOS and Android.
Pika offers self-contained AI creative tools for video, image and sound work. Tools include Video Studio for generating clips up to a 30-second multi-shot video, Color Grade for adjusting color and contrast, Extend Video for lengthening clips with extra frames, and Pika Soundtrack for scoring clips. Character Studio, Image Studio and Product Shot support image creation and editing. Support is available for the web, the iOS app and the API.
A blog post presenting findings and tips on fine-tuning Stable Diffusion with the Dreambooth technique using Diffusers. It describes experiments with hyperparameters and settings, recommending a low learning rate and progressively more training steps, and notes that faces need more steps and prior preservation.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
A blog post by Justin Pinkney explaining how to toonify yourself, making a photo-realistic cartoon model using StyleGAN model blending. It describes transfer learning by fine-tuning a faces model on animated film characters, then swapping layers so low resolution layers give a cartoon face structure while high resolution layers keep photo-realistic rendering.
Magic Eraser is a web tool from Magic Studio that removes objects, people, text, blemishes and patterns from photos. Users upload an image, select the area with a brush, erase with AI and download the result. The source states unlimited free use with no signup, and lists uses such as real estate, photography, fashion, e-commerce and social media.
IOPaint is a free, open-source and fully self-hostable image inpainting and outpainting tool powered by AI models. It can erase unwanted objects, add or replace elements in images, generate text, and generate new pixels around images to enlarge them, with various models available for different tasks.
Polarr offers web and mobile photo and video filters and editing tools. The page lists a Pro editor for iOS, Mac, Windows and web, a beta batch RAW editing AI workflow in the browser called Polarr Next, and 24FPS video effects for iOS and Android.
Pika offers self-contained AI creative tools for video, image and sound work. Tools include Video Studio for generating clips up to a 30-second multi-shot video, Color Grade for adjusting color and contrast, Extend Video for lengthening clips with extra frames, and Pika Soundtrack for scoring clips. Character Studio, Image Studio and Product Shot support image creation and editing. Support is available for the web, the iOS app and the API.
A blog post presenting findings and tips on fine-tuning Stable Diffusion with the Dreambooth technique using Diffusers. It describes experiments with hyperparameters and settings, recommending a low learning rate and progressively more training steps, and notes that faces need more steps and prior preservation.
