Train a LORA with JUST 1 IMAGE!!! - Koyha_ss, A1111, Vlad Diffusion

Опубликовано: 04 Октябрь 2024
на канале: Olivio Sarikas
58,639
1.8k

I trained a Lora with just 1 image. Here is how is my guide on how to train a Lora with just 1 image. I give advice on what to do and what to avoid. I explain my Lora Training Process. I show how to prompt in A1111 and Vlad to get the best Lora results. Also a work-around on how to avoid unwanted results with Prompt Weights

Members Reward Download:
Youtube MEMBERS:    • Post  
Patreon Supporters:   / mushroom-lora-83256233  

#### Links from the Video ####
How to Install and Train with Kohya-ss    • LORA + Checkpoint Model Training GUID...  
ULTRA Sharp Upscale:    • ULTRA SHARP Upscale! - Don't miss thi...  
Ultimate Upscale for slow GPU:    • ULTIMATE Upscale for SLOW GPUs - Fast...  
Controlnet 1.1 Insane Quality:    • ControlNET 1.1 - What you NEED to know!  
Booru Dataset Tag Manager https://github.com/starik222/BooruDat...
(check right side for "latest releases" and download that)
SD 1.5 Pruned Model: https://huggingface.co/runwayml/stabl...

#### Join and Support me ####
Buy me a Coffee: https://www.buymeacoffee.com/oliviotu...
Join my Facebook Group:   / theairevolution  
Joint my Discord Group:   / discord