The training set consists mostly of images from The Most Outrageous Christmas Light Displays of All Time.Clean up the dataset by removing blurry images. Split up 640x480 images into two 512x480 so that there is no down scaling.This version is really quite over the top, putting Christmas light wherever there is room to put one in. Because the training set are all outdoor shots, you need to prompt a bit harder for indoor scenes.This is epoch 11, the rest can be found here: tensor. art/models/808704872812670351/Christmas-Lights-3-NoCD6Co5E11-2024-12-18-21:47:39-Ep-11FLUX.1 - dev-fp8Trigger: christmas lightsRepeat: 20 Epoch: 11 (Seventeen 512x512 image total steps: 4080)Unet LR: 0.0005 Scheduler: cosine Optimizer: AdamWNetwork Dim: 6 Alpha: 3Epoch Loss1 0.4252 0.427 <-3 0.4144 0.3985 0.3866 0.3777 0.3768 0.2569 0.25310 0.242 <- lowest11 0.252
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Idle
Unknown content type
Related Models
Discover similar models you might be interested in
Magical Mass Style - v1.0
High Braid Pony Tail - v1.0
Sausage Dishes - White Sausage-Dev v1.0
Taste of Taiwan - Oyster Thin Noodles v1.0
Jon Foster - V1
Ashley Wood - V1
Dreamy and Colorful - v1.0
Sanai Mahbub Viral Style - v1.0
Artificial Caucasian Girl for Flux - v1.0
Terry & Rachel Dodson - V1
Defaced - V1
Athena - Athena-V1