Weird Wonderful AI Art Blog
58 FOLLOWERS
The Weird Wonderful AI Art Blog explores the intersection of artificial intelligence and the arts. From AI-generated poetry to algorithmic music composition, this blog showcases the ways in which machine learning tools are transforming creative expression. Whether you're an artist, a musician, or simply curious about the latest trends in AI-generated art, this blog is a must-read for..
Weird Wonderful AI Art Blog
2M ago
Flux Dev is an amazing model and produces beautiful images so as we had done in the past, we took it upon ourselves to run the same 4100+ artist names through the model to see where the resemblence of their art is reproduced. This would lead us to believe that said artists images were used ..read more
Weird Wonderful AI Art Blog
2M ago
Flux Dev has certainly grabbed a lot of attention over the past month and a half, I mean most of my posts and youtube content has been focused on Flux Dev. Since its release number of new LoRAs have been released by various community members. One of the featured artists Araminta has been at it ..read more
Weird Wonderful AI Art Blog
2M ago
I’m very happy to share my LoRA Caption workflow for ComfyUI that will let you run a batch of images through two different captioning methods using Florence 2 model or using Clip Interrogator. Both these are paired with WD14 Tagger node which generates some additional tags/keywords for the caption. You can enter the LoRA training ..read more
Weird Wonderful AI Art Blog
3M ago
Araminta who has been featured before on this blog has just released a tutorial video where she trains a new Flux LoRA using her own computer with RTX3090. She walks through the entire process of taking the AI Toolkit by @ostrisai The toolkit seems straight forward to use requires you to use your Huggingface Token ..read more
Weird Wonderful AI Art Blog
3M ago
Flux has two models Dev and Schnell both of which are rated to require upwards of 32GB VRAM, there are other solutions available that let you run Flux under 12GB but if you are truly wanting to explore the power of this model and how good it can be a higher resolution then you need ..read more
Weird Wonderful AI Art Blog
3M ago
Flux has been out of under a week and already seeing some great innovation in the Opensource community. I was working on exploring and putting together my guide on running Flux on Runpod ($0.34 per hour) and discovered this workflow by @plasm0 that runs locally and support upscaling as well. So I ran up my ..read more
Weird Wonderful AI Art Blog
3M ago
August 1, 2024 Black Forest Labs released three new models Flux.1 – Pro, Dev and Schnell. The Pro version is not open source and is available through their API but DEV and Schnell are both open source and available to download via Huggingface page. Dev is a higher quality model than Schnell, but Schnell is ..read more
Weird Wonderful AI Art Blog
3M ago
In this post I will share some Motion LoRA designed to be used in conjunction with AnimateEiff which emulate the basic camera movements like zoom in/out, pan right/left and crane up/down. These Motion LoRA have been trained by Tamás cseh and you can download them here. A Motion LoRA would hook onto the AnimateDiff Loader ..read more
Weird Wonderful AI Art Blog
4M ago
One of the most exciting releases of this week has been the LivePortrait model which was released by KwaiVGI and soon after was incorporated in a Custom Node for ComfyUI by Kijai.
The custom node bring with a sample workflow that can be imported into ComfyUI and you can get started with generating your own animated live character from their image. The workflow is quite simple and all you need is:
Portait image of who you want to animate, could be your own photo or AI generated image
Guiding video – a source video from where the model will take the facial queues and animate the portrait image ..read more
Weird Wonderful AI Art Blog
4M ago
Inspired by the latest post about some really cool LoRAs by Araminta, I got back into training my own LoRA which I had not completed since some time.
The aesthetics of this is based on black and red tones, creating high contrast images with silhouette and reflections of the main subjects. Hence the name Rouge Noir which is french for Red Black.
I had collected my dataset long time ago and was using 50+ images in the original style training but my poor RTX4080 could not handle such size and then I explored Runpod to train my images which was good but I didn’t train this model instead another m ..read more