deforum-for-automatic1111-webui VS sd-multi

Deforum https://github.com/deforum-art/deforum-for-automatic1111-webui

might be deforum (project) (webui extension) or img2img loopback wave (webui extension). it's definitely something with img2img though. that's clear from how it's warping.

Thanks for the workflow. To simplify the process I created a PR that hopefully will make it a bit faster, specially if you're working in rented cloud GPU's.

The sequence after the train with the flashing background is the only exception (1:03 to 1:24), that part was made using the Deforum notebook: https://deforum.github.io/

ive gotten better results applying some color correction to my loops using the same way as they do in deforum https://github.com/deforum-art/deforum-for-automatic1111-webui/blob/automatic1111-webui/scripts/deforum_helpers/colors.py

🔸 Deforum extension for Automatic1111 (Local Install): https://github.com/deforum-art/deforum-for-automatic1111-webui

Deforum plugin settings files: render, coloration. The black and white canny edges + scribble-mode mid-stage rendered video. You can check the prompts keyframing file to see if I got the characters names right. Despite my best efforts, some of the characters appearances were off, I think it was either the character names were incorrectly spelled (I was referring to the Touhou wiki) or they had been underrepresented in the dataset or there was overlap between their naming and some other franchises. There is also the issue of random unrelated characters appearing when the prompt contains no characters and instead is purely abstract, I guess it relates to this specific model retraining.

The sd-multi "meta-fork", which allows running multiple Stable Diffusion systems easily from one place via Docker, has been updated with a few cool additions and changes!

It's running on python anyway, so it's somewhat platform agnostic. You can run "it" on a server https://www.ni-sp.com/how-to-run-deforum-stable-diffusion-on-your-own-cloud-gpu-server/ Aws link https://aws.amazon.com/marketplace/pp/prodview-j557wovfkxxbk or dockerize it https://github.com/arktronic/sd-multi

Awesome, that's much more discoverable and convenient than the script! Just updated my meta-fork to include this update 😀

A little over a week ago I created sd-multi, a "meta-fork" to make it easier to try out different Stable Diffusion forks/frontends/etc. using either WSL2 or native Linux, with Docker.

Whoa, that web UI looks like a huge improvement from the previous one! Nicely done! I'll update my meta-fork to this version soon.