Directory
Published directory entries matching your search.
A blog post explaining CLIP, a transformer model from OpenAI that matches text embeddings with image embeddings. It offers high-level prompt engineering tips for generative art and includes over 3500 prompt output examples, along with a section of Colab notebook links.
CLIPasso is a method for converting an object image into a sketch with adjustable abstraction levels while preserving key visual features. It optimizes Bézier curves using a differentiable rasterizer and a CLIP-based perceptual loss, without requiring an explicit sketch dataset. Abstraction is controlled by varying the number of strokes.
Deep Art Effects is software that turns photos and videos into neural art using artistic style transfer of famous artists. It also offers image processing such as scaling images to four times the original size and automatic background cutout, with processing running offline on the user's PC.
This GitHub repository hosts the official code for DragGAN, a project presented at the SIGGRAPH 2023 conference under the title 'Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold'. The repository includes links to web demos, requirements documentation, and instructions for running a Gradio visualizer in Docker.
DreamBooth is a method for personalizing text-to-image diffusion models. Given a few images of a subject and its class name, it fine-tunes a pretrained model so a unique identifier refers to that subject, allowing synthesis of the subject in new scenes, poses, views and lighting, with tasks including subject recontextualization and text-guided view synthesis.
pixray-text2image is a public Replicate model that uses pixray to generate an image from a text prompt. It runs on Nvidia T4 GPU hardware, with predictions typically completing within 6 minutes, and is also open source and runnable on one's own computer with Docker.
Easy Diffusion is an easy to install distribution of Stable Diffusion, the open source text-to-image AI software. It installs the required software components and provides its own web interface for free. Users run a simple installer, then create images from text prompts or use images to direct the AI. An active community is available on Discord.
Find all the trending and useful Gradio demos that you can use to edit your images.
Creates or edits images with generative models and visual controls.
Hotpot.ai is a service for creating and editing images and videos with AI. Users can generate images from a few words, animate a favorite image, and produce AI headshots from a photo. The site also offers photo upscaling, colorizing, restoring and background removal.
Topaz Labs: AI Image Quality Software: "professional grade workflow, with many features" (this is an affiliate link by nejcsusec.beehiiv.com).
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
ImageFan Reloaded is a cross-platform, tab-based image viewer written in C# that targets .NET 10 on Linux and Windows. It supports multi-core processing for thumbnail generation and browsing across multiple folder tabs, with 46 supported image formats and browsing within zip files.
A Hugging Face Space by preSalesAIAutomation that accepts an uploaded image and a description and produces a video animation. The page states the app outputs a high-quality video with realistic motion and dynamic scenes based on the input. The Space is listed as running on Zero.
imutils is a Python package of convenience functions that make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV. It works with Python 2.7 and Python 3 and is pip-installable given NumPy, SciPy, Matplotlib and OpenCV. A find_function method searches function names across modules.
