Astria is an AI image production platform that creates ecommerce visuals and headshot products. It provides tools for training custom models, generating images, and delivering outputs, with additional offerings including API access, a Photoshop plugin, and style templates for headshots and ecommerce use cases.
A page by pharmapsychotic collecting tools and resources for AI art, organized into sections such as text to image, upscaling, StyleGAN, text video, prompt engineering and music. It links to shared Google Colab notebooks for text-to-image work with pre-trained GAN and diffusion models, and notes Stable Diffusion WebUI for running SD locally.
Pixray is a service that supports photographers and agencies in generating predictable revenue from copyright violations in line with their brand and values. It operates Fair Licensing, a copyright enforcement platform that allows agencies to resolve copyright claims by selling retroactive licenses without lawyers or middlemen.
An online tool that removes video backgrounds using AI, accepting MP4, MOV and WEBM files. Free exports are 720p MP4 with a light watermark, while Pro allows 4K export without a watermark. Files are auto-deleted within one hour and are not used for training.
A blog post by Matt Webb arguing that Adobe should make a boring app for prompt engineers. It discusses AI image synthesis tools like DALL-E 2, Imagen, and Midjourney, noting that prompt engineering is a new kind of expertise. The post describes Midjourney's Discord-only interface during its beta.
A gentle illustrated introduction by Jay Alammar to how Stable Diffusion works, covering the components of Stable Diffusion, what diffusion is, painting images by removing noise, diffusion on compressed latent data, and the text encoder. It focuses on image generation from text only (text2img) and includes translations into Chinese and Vietnamese.
An AI platform for generating images and video from prompts, described as free to start. It also lists creation of characters and audio, and states that output is private by default.
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 page by pharmapsychotic collecting tools and resources for AI art, organized into sections such as text to image, upscaling, StyleGAN, text video, prompt engineering and music. It links to shared Google Colab notebooks for text-to-image work with pre-trained GAN and diffusion models, and notes Stable Diffusion WebUI for running SD locally.
Pixray is a service that supports photographers and agencies in generating predictable revenue from copyright violations in line with their brand and values. It operates Fair Licensing, a copyright enforcement platform that allows agencies to resolve copyright claims by selling retroactive licenses without lawyers or middlemen.
An online tool that removes video backgrounds using AI, accepting MP4, MOV and WEBM files. Free exports are 720p MP4 with a light watermark, while Pro allows 4K export without a watermark. Files are auto-deleted within one hour and are not used for training.
A blog post by Matt Webb arguing that Adobe should make a boring app for prompt engineers. It discusses AI image synthesis tools like DALL-E 2, Imagen, and Midjourney, noting that prompt engineering is a new kind of expertise. The post describes Midjourney's Discord-only interface during its beta.
A gentle illustrated introduction by Jay Alammar to how Stable Diffusion works, covering the components of Stable Diffusion, what diffusion is, painting images by removing noise, diffusion on compressed latent data, and the text encoder. It focuses on image generation from text only (text2img) and includes translations into Chinese and Vietnamese.
An AI platform for generating images and video from prompts, described as free to start. It also lists creation of characters and audio, and states that output is private by default.
