My final tool is AUTOMATIC1111's Stable Diffusion web UI "A browser interface based on Gradio library for Stable Diffusion", as they describe it. In the app prefereces you can set the model location to any folder you'd like. In Mochi Diffusion it is completely up to you where you store your models. Mochi Diffusion generating an image via AI on macOS Mochi Diffusion model storage folder Hidden in their wiki there is a page on How to convert ckpt or safetensors files to Core ML Fortunately the developers composed a list on Hugging Face with all converted Core ML models. Since Mochi Diffusion is using Core ML, you can only use AI models compiled to Core ML models. I have no doubt that they'll eventually add image to picture and other features. It currently just supports text to image. At the moment, I see a new release virtually daily. They release their work at an astounding rate. Due to the fact that DiffusionBee is an Electron application, MacOS functionalities were not utilized.ĭevelopment on Mochi Diffusion is very active. This was a significant improvement over DiffusionBee. A framework tailored for the M1 processor in my computer. Mochi Diffusion is a native Mac app working on the Core ML framework. Given that I use a Mac, this was a major advantage. It had a great advantage over DiffusionBee: Core ML support.Ĭore ML is optimized for on-device performance of a broad variety of model types by leveraging Apple hardware and minimizing memory footprint and power consumption. Mochi Diffusion which currently only supports text to image was the second tool I explored. Here are all models and generated images stored. Since I don’t have infinite disk space I was quite curious where all these models were stored. When I first stated DiffusionBee it downloaded 8.5 GB of AI models. Time to look for another tool.ĭiffusionBee generating an image via AI on macOS DiffusionBee model storage folder Their Github showed a last commit of November 23 last year. With new techniques and innovation in the field of AI image generation I noticed DiffusionBee wasn’t keeping up. Unfortunately I didn’t succeed in loading any custom model successfully. DiffusionBee supports: Text to Image, Image to Image, Inpainting and Outpainting.ĭiffusionBee is able to load custom models. The first app I've used on my Mac Studio was DiffusionBee It is described as “Stable Diffusion App for AI Art”. In this folder you'll find Data/Library/Application Support/model_zoo which contains all the models DiffusionBee This folder will show up in your terminal as a large GUID like 7D9459A9-60E1-4A50-84AC-D23B3F10478F, therefore use Finder. After some searching I've found ~/Library/Containers/ which contains the folder Draw Things. I really wondered where all the models were downloaded because they take lots of diskspace. For Draw Things, however, all you need to do is choose your chosen model, and Draw Things will download it immediately.ĭraw Things suporrts many models out of the box Draw Things model storage folder The majority of the time, downloading the models requires going to a website. Installing the appropriate models could be difficult for many programs. Draw Things turns out to have a wonderful desktop user interface (UI), which makes it very simple to use on your desktop Mac.ĭraw Things generating an image via AI on macOS Ventura Of course, running iOS apps on macOS is possible with an Apple Sillicon processor. Just the cheapest one out there with a Apple M1 Max and 32GB of RAM, running MacOS Ventura 13.1 Draw Things for macOS Fortunately my Mac Studio could achieve way more than I expected. When Stable Diffusion and Dall-E were introduced, I thought this was only for people with a decent video card in their computer. I was blown away that this actually ran locally on iOS.ĭraw Things generating an image via AI on iOS When installed, it downloads the models and off you go. Instead of a cloud service, these AI images were generated on my iPhone!. Outpainting - You provide a source image and tell the AI what it should draw outside of the source image boundaries.Īfter some time a friend introduced me to Draw Things This was a special app.Inpainting - You mask a part of the image and tell the AI what to draw in that masked section.Image to Image - You provide a source image and tell the AI what you would like to see on the generated image.Text to Image - You write in text what you want the AI to draw.In this article I will use some terms regarding AI image generation:
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |