text2image-gui VS diffusionbee-stable-diffusion-ui

I read github

With the AMD guide

You can find NMKD here, and the readme should be quite simple to get it to work on your own machine for a basic SD setup: https://github.com/n00mkrad/text2image-gui

So assuming you are suing the "NMKD" GUI i found an existing issue on the github page: The Issue.

Source code is available here if you want to check that out, the download for the precompiled program is on itch.io.

The 1024x572 was from a comment talking about NMKD ,that mentions using OptimiseSD may run on less than 4GB.

Be sure to read the system requirements and the special AMD GPU info page.

Easiest way I have seen so far, working well for me. https://github.com/n00mkrad/text2image-gui/blob/main/DreamBooth.md

* LLaVA model: I'll add more documentation. You are right Llava could not generate images. For image generation I don't have immediate plans, but checkout these projects for local image generation.

- https://diffusionbee.com/

- https://github.com/comfyanonymous/ComfyUI

- https://github.com/AUTOMATIC1111/stable-diffusion-webui

Interesting, will check it out to see how it compares with https://diffusionbee.com which I am using for last few months for fun.

It depends on what you are planning to do. Stable diffusion works great locally on both the dell+linux and the mac laptop I tried it on. This one was easy to use while exploring models from huggingface: https://diffusionbee.com/

diffusion bee is the easiest app to use.

If you have a Mac, I highly recommend DiffusionBee. It’s an app you can install on your computer and use as much as you want (even offline) for free. The website has older downloads but if you go here you can get the latest beta with more features: https://github.com/divamgupta/diffusionbee-stable-diffusion-ui/releases

Try these first: 1. https://drawthings.ai/ 2. https://diffusionbee.com/

Diffusion Bee

If you have a Mac, you can try this out too offline for free - https://diffusionbee.com (Go into the settings to make it the largest image size and you can also upscale it afterward - helpful for submitting larger artwork dimensions to distributors).