Inspired by some collage images I saw on Midjourney which emulates newspaper clippings which are glued to form shapes or characters, i was inspired to create a SDXL LoRA (Low Rank Adaptation) style that would emulate this to some degree. As I have documented by...
I wanted to train a LoRA style this time but as I had done before in my post Training my first SD LoRA, this time I was struggling to get it going. The issue was I for style training which was an aesthetics I wanted I had to have large data set 100+ images for SDXL...
Midjourney just release their latest Upscaler for v5 images that can take your standard (1:1) 1024px image to 2x and 4x resolution while maintaining the details and creating artifacts. Well that's the concept so one needs to explore this and see what is the big...
In this post I would like to share some of the keywords that I have used and found influence the composition which comprises of the Camera Position (distance of camera from subject) and the Camera Angle (where the camera is place relative to the subject). Although...
ComfyUI is one of those interfaces that you need to get comfy with. If you are intimidated with it then you won't like it, nor would you spend the time in learning it. Its the same case when I tried to learn Capture One Pro a photo editing software (very good for...
Inspired by a post by @rainisto where he shared how he created an AI character (women) using Midjourney and then trained a Stable Diffusion (SD) v1.5 Low Rank Adaptation (LoRA) so that you can create consistent character of the women in different settings. This...
I got a few comments on this post related to the Spiral illusions that are all the rage at the moment using SD1 QRCode Monster ControlNet model. It seems that there may not be enough ControlNet based ComfyUI interfaces available on the web. If you use A1111 then you...
Trending right now there is a who flurry of images being generating using spiral optical illusion that is embedded inside the image generated using stable diffusion. The result looks quite intriguing and this is not just limited to spirals you can use any other kind...
ComfyUI is a powerful and modular stable diffusion GUI and backend that is deemed to be better than Automatic1111. Also, having watched the video below, looks like Comfy the creator works at Stability.ai which means this interface will have lot more support with...
SDXL came out for public use last week and I spent most of the time testing and playing around with this new model locally. I then stress tested by GPU by running close to 4000 prompts back to back generating images that will try to emulate the Artist styles that SDXL...
SDXL 1.0 (Stable Diffusion XL) has been released earlier this week which means you can run the model on your own computer and generate images using your own GPU. I wanted to document the steps required to run your own model and share some tips to ensure that you are...
This is mind numbingly simple, yet so powerful that once you understand what you can do with you can create some very powerful attention grabbing videos using AI. In particularly we are talking about ControlNet 1.1 in conjunction with Stable Diffusion. The concept and...