DEV Community

Cover image for Started empirically experimenting for finding the best training hyper parameters for Stable Diffusion 1.5 based models
Furkan Gözükara
Furkan Gözükara

Posted on

Started empirically experimenting for finding the best training hyper parameters for Stable Diffusion 1.5 based models

#beginners #tutorial #ai #opensource
  1. Using Kohya SS GUI as trainer script.
  2. Rented 8 GPU machine from RunPod and already doing 8 different trainings right now.
  3. If you have any input / feedback / suggestion let me know please.

Image description

Image description

Image description

Top comments (0)

Read next

pauq profile image

Scraping New Telegram Channels

pauq -

koolkamalkishor profile image

Evaluating Medical Retrieval-Augmented Generation (RAG) with NVIDIA AI Endpoints and Ragas

KAMAL KISHOR -

mikeyoung44 profile image

LLM Quantization: Balancing Accuracy and Efficiency for Real-World Deployments

Mike Young -

mikeyoung44 profile image

EmbodiedRAG: Dynamic Scene Graphs for Efficient Robot Task Planning in Real-World Environments

Mike Young -