Diffusers
Overview
Diffusers is a Mac application designed to generate images from text descriptions of what you would like to create. It uses state-of-the-art models contributed to the Hugging Face Hub, and is optimized and converted to Core ML for maximum performance.
Diffusers includes five models: Stable Diffusion 1.4, Stable Diffusion 1.5, Stable Diffusion 2, Stable Diffusion 2.1 and OFA small v0. Each model has its own style and personality, so users can choose which model best suits their needs.
The application allows users to tweak generation parameters to help create the desired image. These include the model to use, the prompt, negative prompt, seed and steps.
The prompt is the description of what you want, while the negative prompt is what you don't want. The seed allows reproducing a previous generation, while the steps control how many diffusion steps the image generation will take.
Diffusers is privacy-focused and does not collect any data. Additionally, it is open source and has a permissive license. It is free to use and is currently being developed for iOS/iPadOS support.
Releases
Top alternatives
-
Arvoly XSL🙏 116 karmaOct 31, 2023@Photo AIIt's not free, it forces you to input an email before shoving a price tag in your face.
-
-
Freepik helps people to create better designs, faster.
-
-
Six months ago I was building some landing pages and found myself wasting way too much time downloading stock photos, cropping them, resizing, rehosting... the whole thing felt broken. I looked around for a tool that just let me describe the image I wanted and get it in the right format instantly—but nothing really existed. So I built Inliner AI. Now when I need an image, I just write what I want directly into a URL like this: https://img.inliner.ai/my-project/panda-playing-guitar-on-stage_1200x750.png Hit enter and boom Inliner generates an original AI image, intelligently cropped, resized for the web, and served instantly via CDN. Need a quick edit? Just append it to the URL: .../remove-the-guitar_900x750.png No uploads, no UI, no waiting. You can also upload your own products, people, or logos and compose them into generated scenes. For more control, there's a Studio web GUI where you can play with prompts and dimensions and compare variants side by side before committing. Where this gets really powerful is when you show your LLM how to use these URLs. Once it knows the pattern like: https://img.inliner.ai/my-project/xxx-yyy-zzz.png It can generate, tweak, and iterate on image assets dynamically, right inside your prompts or your code. Everything stays self contained in the link. We also include copy/pasteable instructions for Claude, GPT, Cursor, and more so you can wire this up in minutes. If you're building a product, designing a page, or just prototyping something new try it out and let me know what you think!

