stable-diffusion-webui-colab VS deforum-for-automatic1111-webui

- Go to this link: https://github.com/camenduru/stable-diffusion-webui-colab

if yes then you can use camenduru's github repository, here is the link, you can read the guide there. With it, you don't need to use your local device to run stable diffussion but using google colab intead

Google colab + https://github.com/camenduru/stable-diffusion-webui-colab + Go to civit.Ai and look at the best pictures for a model that you like. Copy their positive and negative prompt.

You can also run it for free without even downloading it using Google colab Link: https://github.com/camenduru/stable-diffusion-webui-colab

camenduru/stable-diffusion-webui-colab: stable diffusion webui colab (github.com)

It will be installed on the temporary drive, so it will take more time to start, but you can choose the model beforehand: https://github.com/camenduru/stable-diffusion-webui-colab

I primarily use camenduru's colab version: https://github.com/camenduru/stable-diffusion-webui-colab

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.