PyTorch Implementation of No Token Left Behind: Explainability-Aided Image Classification and Generation.
Caricature Maker is an online AI-powered tool that generates personalized, humorous caricatures from user-uploaded photos. Users do not need design skills to use the service, and generated caricatures can be used for profile pictures, gifts, or social media. As of the listing, over 3,000 creators had used the tool to produce more than 9,000 caricatures.
Generrated is an image and prompt reference and inspiration resource containing 9,300 images generated using DALL·E. Clicking an image shows the prompt used to generate it along with three additional images generated alongside it. The site owner plans to add more DALL·E 3 images to allow comparisons with their equivalent DALL·E 2 versions.
bugfree.ai is an interview preparation site for software engineering roles, covering system design, object-oriented design, data and behavioral questions. It provides guided walkthroughs, example answers and AI-powered feedback, plus real interview experiences.
RunDiffusion is a platform providing access to AI models for image generation, image editing, upscaling and video creation. It offers open source tools including ComfyUI, Fooocus, Auto1111 and Kohya, and states that workflows can chain tools for business use cases. A public API covers boards, generations, reporting and uploads.
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.
Image Super-Resolution (ISR) is a project that aims to upscale and improve the quality of low resolution images. It contains Keras implementations of Residual Dense Networks for Single Image Super-Resolution, along with scripts to train these networks using content and adversarial loss components. Pre-trained models include RDN and RRDN variants.
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
Caricature Maker is an online AI-powered tool that generates personalized, humorous caricatures from user-uploaded photos. Users do not need design skills to use the service, and generated caricatures can be used for profile pictures, gifts, or social media. As of the listing, over 3,000 creators had used the tool to produce more than 9,000 caricatures.
Generrated is an image and prompt reference and inspiration resource containing 9,300 images generated using DALL·E. Clicking an image shows the prompt used to generate it along with three additional images generated alongside it. The site owner plans to add more DALL·E 3 images to allow comparisons with their equivalent DALL·E 2 versions.
bugfree.ai is an interview preparation site for software engineering roles, covering system design, object-oriented design, data and behavioral questions. It provides guided walkthroughs, example answers and AI-powered feedback, plus real interview experiences.
RunDiffusion is a platform providing access to AI models for image generation, image editing, upscaling and video creation. It offers open source tools including ComfyUI, Fooocus, Auto1111 and Kohya, and states that workflows can chain tools for business use cases. A public API covers boards, generations, reporting and uploads.
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.
Image Super-Resolution (ISR) is a project that aims to upscale and improve the quality of low resolution images. It contains Keras implementations of Residual Dense Networks for Single Image Super-Resolution, along with scripts to train these networks using content and adversarial loss components. Pre-trained models include RDN and RRDN variants.
