nextjs-notion-starter-kit VS ControlNet

I love coming across a great blog like this an realizing it was built using two of my open source repos:

- https://github.com/transitive-bullshit/nextjs-notion-starter...

- https://github.com/NotionX/react-notion-x

Here is a repo I used as a starting point before (repo is not mine) https://github.com/transitive-bullshit/nextjs-notion-starter-kit

The github page: https://github.com/transitive-bullshit/nextjs-notion-starter-kit

Most of services tried to take money from me for custom domains, sitemap, theme etc. Sorry, I don't have enough money for that. 2. nextjs-notion-starter-kit This was the second for me. ① Cannot handle path well It is OK to map your page to /one but it throws 404 error when path is /one/two or /one/two/three. Since I have to map URL like /category1/subcategory2/sub-subcategory3/sub-sub-subcategory4/page5, this is serious problem. Other than that, it seems quite nice. 3. loconotion ① Does not sort pages in directories I tested this without mapping pages to path, but it seems it doesn't sort pages in directories when processing Notion pages. I found python script that sort those pages, but it doesn't support Windows, the only OS I use for general use. ② Slow generation If my site have few pages, it might be good choice, but my site has ~100 pages and a lot of pages will be added in near future. If it converts every pages whenever I launches it, it would take a lot of time. 4. Fruition I think it is just converting Notion page URL into mapped URL. Kind of nice, but still slow as Notion's shared page is. But I think it is doing some 'magic'. I didn't know that CF Worker can do such job. I'm currently using this.

If you want more control over your website via React, then we recommend checking out the accompanying Next.js starter kit, which is free and uses react-notion-x under the hood.

https://transitivebullsh.it

It's powered by Notion as a CMS, react-notion-x, Next.js, and Vercel.

I published an open source starter kit so anyone can easily create similar sites: https://github.com/transitive-bullshit/nextjs-notion-starter...

source code

It`s all possible. Have a look into Automatic1111`s Web UI, ControlNet, OpenPose and, if you don`t have a dedicated GPU with at least 8GB of VRAM, or at least 16GB of RAM to use the CPU, you can also use Stable Horde to use the webUI with a peer-to-peer connection, where you`ll only use a fraction of your resources, but you`ll be able to use local AI models with all the bells and whistles that you won`t get from "state-of-the-art" paid services.

Next up is ControlNet. Controlnet, as Illyasviel--creator of controlnet--describes it, "let's us control diffusion models!." ControlNet is a neural network structure to control diffusion models by adding extra connections. [8]. There is more to that than what I described, but the big take-away is that ControlNet takes a preprocessed image that you provide (or is generated) and uses that as a way of constraining the output the sampler's noise generates, allowing you to have a bit more control of the output. ControlNet is typically used for character or scene "artwork", which previously would have been a challenge with just prompting alone (at least with this current architecture).

For your first part of the comment, I can simply refer you to technologies like ControlNet, LoRA and prompt embedding: https://github.com/lllyasviel/ControlNet https://github.com/microsoft/LoRA

Here you can see what every controlnet preprocessor and model do, to give you an idea of ​​how to use

Ya, it takes awhile to really start getting comfortable with the wonkiness. If you are trying to do something specific, look for a LoRA, but in general I'd recommend you get controlnet so you can feed it a reference image. Another simple trick is to edit the image a bit in GIMP or a photo editor to get the color scheme you like and then feed it back to img2img at low denoising (0.1-0.2) to refine it. You can also add just garishly bad cartoon drawing or photoshop in assets and img2img will usually make something of them and blend them into your image, I find this easier than using img2img scribble.

If there are no errors, go to the "Extensions" tab, then "Install from URL". There, enter "https://github.com/lllyasviel/ControlNet" then click "Install".

This is a good place to start reading. Given the open-source nature of SD, there are setups of various difficulty available. A1111 is the "standard" people enjoy because it's easy to plug in new stuff (ControlNet, new models, etc.), but it's not inherently easy to set up and get going. There is an installer for it, but I haven't tried it.