AI Art Thread XXVIII

Backends:

>https://github.com/LykosAI/StabilityMatrix
This is more of a one click manager that you can install / run the other backends though. Easiest by far. Recommended to download Forge through it and use its built-in Civitai browser to download models with.

For models not on Civitai just download and drop them in Stability_Matrix\Data\Models\* (lora folder if a lora, TextualInversion if embedding, stablediffusion if checkpoint)

>https://github.com/lllyasviel/stable-diffusion-webui-forge
Faster / more efficient version of Automatic1111 with some helpful extensions built-in. I would recommend installing this through Stability Matrix.

>Stable Diffusion Automatic1111
https://github.com/automatic1111/stable-diffusion-webui
The original for posterity's sake.

>ComfyUI
https://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#installing
Has a learning curve but is extremely customizable and usually has the latest methods / papers implemented first.

Models:

>Pony Diffusion V6 XL checkpoint for Stable Diffusion
https://civitai.com/models/257749/pony-diffusion-v6-xl?modelVersionId=290640

>Autism Mix (Alternative model based upon pony diffusion)
https://civitai.com/models/288584?modelVersionId=324619

>Useful artist style LoRA:
https://civitai.com/models/317578/pdv6xl-artist-tags?modelVersionId=356175

>LoRAs by /mlp/:
https://rentry.org/ponyxl_loras

>LoRAs by /h and other useful info:
https://rentry.org/ponyxl_loras_n_stuff

>How to make your own LoRA:
https://rentry.org/59xed3
https://civitai.com/articles/91/how-to-correctly-obtain-images-for-a-dataset
https://civitai.com/articles/3522/valstrixs-crash-course-guide-to-lora-and-lycoris-training
https://civitai.com/articles/4100/how-to-create-a-style-lycoris-for-ponyxl-on-low-vram-locally

>AMD USERS (note for AMD GPUs using Linux is like 4x faster)
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs
Further advice
https://desuarchive.org/mlp/thread/40794982/#40797301

>Prompt tips for new users:
Grab a image you like the style of from the desired model's citvia's site and drop it onto the PNG info tab in SD, you can then click send to text to image to reuse its generation info for your own images. Change the seed so you do not get just the same image. I'll work on making a prompting guide soonish.

>No, AI art is NOT stealing.
Here, all the usual misinfo already addressed in one easy place for your viewing displeasure:
https://www.youtube.com/watch?v=F-i09Nz96cw

>Previous Thread
>>40920618

>Past Threads
https://desuarchive.org/mlp/search/subject/ai%20art%20thread/

Christmas In July Edition

>/shy/thread Ponepaste (includes the OP, writefag list, writefag request bin, and all current/completed stories)
https://ponepaste.org/user/FluttershyThread

>Collaborative Fluttershy playlist (request for new content to be added in the thread)
https://www.youtube.com/playlist?list=PL1pZSbhMdtwnQJZ2vx1OojIw8Ue0o9Uxy

>/mushy/ Musical mixtape (request for new content to be added in the thread)
https://www.youtube.com/playlist?list=PL1pZSbhMdtwlV6Vdoba4EvN7tpXBBZmQ7

Previous thread:>>38804858 (You) (Cross-thread)

Can you faggots please stop picking on the Flutterfags? They did nothing to deserve this. They've always been some of the quietest and kindest waifufags.

Which waifufags do you think have suffered the most? I'm thinking either ponkfags or flutterfags.

Are any other waifufags anxious about s9 completely cucking us and killing any chance of a relationship with our pony waifus?

What did they mean by that?

I LOVE ALL OF YOU SO FUCKING MUCH

we're all gonna make it bros /)

Imagine…

What would their universe be line if Luna actually won instead?

What are the implications of AI being able to replicate the style of artists that have abandoned pony?