Training Flux Lora #melies

try train LoRa on FAL.ai to see if it works #photoai

Trained flux dev multi Lora works just enough for MVP. #nbpai

add Sinterklaas LoRa #photoai

train a few lora's on flux.1 #wondermachine

train neon tokyo LoRa #photoai

try 🧶 Yarn LoRa #photoai

Train Flux LoRA fal.ai/models/fal-ai/flux-lor… #fajarsiddiq

train GTA: San Andreas style LoRa #photoai

fix results from Codeformer or GPFGAN different than Clarity because I loaded a LoRa for those #photoai

switch #therapistai fully to Llama3-70B

download Llama3-70B and Llama3-8B #life

Add pagination because we now have 100+ LoRA's and loading them all at once was a bit slow #lora

Training Flux Lora on myself #melies

Trained a basic flux lora model on replicate… need more fine tuning tbh #nbpai

switch #therapistai to Llama 3.1

publish San Andreas LoRa x.com/levelsio/status/1834596… #photoai

upload my Analog Film LoRA to Civitai #photoai civitai.com/models/875859

🤖 Updated some scripts to use Ollama's latest structured output with Llama 3.3 (latest) and fell back to Llama 3.2. I drop from >1 minute with 3.3 down to 2 to 7 seconds per request with 3.2. I can't see a difference in the results. For small projects 3.2 is the better path. #research