Back
Similar todos
test Vision model coop with Llama3 
#therapistai
Add support for lensing 
#figurine
installing relalistic vision model on a1111
add open source vision model to #therapistai so it can read screenshots and see images/photos
if message sent with image, save the image as prompt_image, then describe it with Llava vision model and send to Groq API #therapistai
try new AI model we made with 3d vision + 3d room segmentation for 
#interiorai
Added support for GPT-4 Vision 
#pdfpals
Adding support for the new FLUX text-to-image model 
#boltai
investigate depthmaps and vision api
prototype a simple autocomplete using local llama2 via Ollama 
#aiplay
LoRA training for models 
#melies
Play around with OpenAI Vision API 
#jomresplugins
Use Android vision library for OCR
Improve LoRA training #melies
Added new pinch based on vision pro documentation 
#handkit
