AI Art Thread #30
Backends:
>https://github.com/LykosAI/StabilityMatrixThis 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 through the in-built downloader 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-forgeFaster / more efficient version of Automatic1111 with some helpful extensions built-in. I would recommend installing this through Stability Matrix.
>Stable Diffusion Automatic1111https://github.com/automatic1111/stable-diffusion-webuiThe original for posterity's sake.
>ComfyUIhttps://github.com/comfyanonymous/ComfyUI?tab=readme-ov-file#installingHas a learning curve but is extremely customizable and usually has the latest methods / papers implemented first.
Models:
>Pony Diffusion V6 XL checkpoint for Stable Diffusionhttps://civitai.com/models/257749/pony-diffusion-v6-xl?modelVersionId=290640>Autism Mix (Alternative model based upon pony diffusion, I prefer the DPO version of it. Better anatomy / more coherent.)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/59xed3https://civitai.com/articles/91/how-to-correctly-obtain-images-for-a-datasethttps://civitai.com/articles/3522/valstrixs-crash-course-guide-to-lora-and-lycoris-traininghttps://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-GPUsFurther 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. For tags on e621 use underscores between multi word prompts.
zPDXL Quality Embedding:
https://civitai.com/models/332646/pony-pdxl-negative-embeddings?modelVersionId=372656>No, AI art is NOT stealing.Here, all the usual misinfo already addressed in one easy place for your viewing displeasure:
[YouTube] The Most Common Arguments For & Against AI (embed)
>Previous Thread>>40953572>Past Threadshttps://desuarchive.org/mlp/search/subject/ai%20art%20thread/ 