I made some tweaks to the look of the web app and made it more obvious when the user was waiting for an image to be generated When the image is being generated, the button and text box for input are blurred and disabled and a message overlayed over the image frame. This way users…

After some further tweaking with getting Node to run python within a conda environment, I got the features in the stripped down version working. I now have an web app that uses node to run a python script which generates an ‘advertisment portrait’ image based on personal input from the user. The input is then…

Based on my tutor’s feedback I am going to make something around these points html page with image placeholder. textbox input Using node for backend, user can click button to submit a word that they enter The word is submitted, possibly using an endpoint of the node server The word is added to other keywords…

I have found that the img2img does not make it easy to access the intermediate frames after much trial and error. I have found another package https://github.com/nateraw/stable-diffusion-videos that may be able to do what I need but it will need tweaking. It looks like by default this package generates actual video output by providing two…

Trying to get THIS repo working on macbook Cloned repo – tried to install environment.yaml and got Some of the reading I’ve done about getting diffusion working on apple silicon has said these devices can’t use cuda anyway so I commented out the line for this package in the yaml file. There were other problems…

Going to try and get stable diffusion up and running again locally. In doing this I should bare in mind that what I’ll use on my macbook will likely be different from what I end up using for exhibiting my work, since the exhibition machine will probably be windows and I know there have been…

I spoke with my supervisor and talked her through a mindmap that I had created as part of my research After spending around 10-15 minutes talking through in more detail each point, she told me that this represents significant progress in my research. The conversation was recorded for these parts. I was very pleased that…

I began working on the display aspect of my project. I needed this display to be able to show images as the image generation element of my project produces images. Ideally, the images would be shown more as ‘frames’ in a video or animation rather than being seen as separate and distinct images. I started…

After a meeting with my supervisor I decided that I should dedicate more time this week to the research and thesis side of things. We also discussed the possibility of me delivery parts of my thesis/ report as videos rather than in writing. I think I will bear in mind that it would be useful…

This was a fairly quiet week for me due to personal circumstances. However I did have a tutorial with a technician to get a feel for how feasible he thought some elements of my project are. He expressed confidence that it should be possible to meet at the very least the minimum requirements I settled…