This lora was trained for 90 epochs using onetrainer on a dataset of 63 high-res frames from Twin Peaks, Mulholland Drive, Blue Velvet etc. It focused on color grading, so no trigger words are required. For caption-based prompting I use qwen captioner to generate prompts for examples.
Works normally on 1.0-1.2, you can mix it with another realism loras as well.
Description
FAQ
Comments (12)
Looks really cool! Can you share your workflow?
thanks, i will, soon
upd added some examples with metadata, enjoy
Sometimes you didn't know you needed something until you find it. This is one of the best of those times. Thank you for this, great work!
im so happy!
Person reading this not imagining you would ever need such a thing.. this is an excellent tool to create moments that will amaze you. Start out with a negative value to understand what is possible!
Thank you for your excellent lora. :)
ah thanks for all kind words! enjoy
i still dont know who is david lynch but this is good
its the best time to watch something from david lynch
Lora Palmer, very nice🤓