0a9bbf5d

LLM: CoT Reasoning, VRAM efficient deployment, function calling, HA integration, RP (because sometimes I want to escape into *another* dystopian world) T2I/I2I: Lora Training, ComfyUI, testing out the limits of realistic image generation (mostly with Flux these days) T2V/I2V: Just playing with Wan2.1 :) T2A: Who doesnt want an AI Assistant with SHODANs voice, right? Otherwise interested in creating fitting character voices for RP. A2T: Finally converting my audio note archive to text (mixed english+german ramblings) Music Gen: Mostly played with SUNO and YuE and then post-processing with AudioSep and basic-pitch to get MIDIs, but would love to try some other models ... not exactly happy with my setup yet.