AI workshop

Prompt crafting

Stable Diffusion 1.5

Stable Diffusion 2.1 (sometimes slow/busy)



Stable Horde (occasionally slow!)
check also Interrogation option for image captions.

Camenduru webui: , slow and this works better as local installation, then it is possible to use multiple fine-tuned image models.

Inpainting / generative fill:
Adobe generative fill

Testing various fine tuned SD-models.

Image Mixer

gen-2 text-2-video
audioldm-text-to-audio-generation (text-to-speech)
virtual avatar

*** images for the workshop ***

Aaron Hertzmann – When Machines Change Art
Lev Manovich & Emanuele Arielli – Artificial Aesthetics chapter 5 (PDF -> “Media Translations”)
Vinoy Laughner – Computer Art: Is It Really Art?

Additional links: (Camenduru webui explained and installation instructions, notice min. 4GB GPU required)
pix2pixHD next-frame-prediction (used on FATUM)