Satoshi Urushihara Style - Urushisato V15
by ModelsLabthis is a huge 384 dim LoRA, experimenting with adaptive learning ratenote I tried resizing this LoRA to lower dims using the kohya_ss tools, but the quality results were too subjective (some images degrade, others are improved)training settings3137 training images512,512 training resolution16 epochs, 6,384 steps, 8 batchesnetwork dim & alpha 384DAdaptAdam optimizer, constant schedulerlearning rate 1.0bucketing & random cropuseful optional tokensurushisato tagged on all images for general style boostova tagged on all screencaps from animationbackground tagged on any image that has no human subject
satoshi-urushihara-style-urushisato-v15Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Unknown content type
Related Models
Discover similar models you might be interested in
![hana makihatayama ( ) - magical doremi (ojamajo doremi) [Illustrious + pony + SD1.5] - v2.5](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/edeaa905-9fc1-45cb-df8b-1909cdcdba00/width=512/653237.jpeg)
![[SD1.5] OpenSolera - Anime Mix - OpenSolera-α5 [Serif]](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/5d74b8dd-0609-403d-8afc-21bd10de7c66/width=1024/33465999.jpeg)
![Safi'Jiiva [1.5/SeaXL/Noob | Monster Hunter] - v1 - BB95 Alt](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/25b43a13-15ac-4abf-9e23-630da0198124/width=96/Valstrix.jpeg)
![[FLUX.1 D&XL&1.5] 2B ( YoRHa No.2 Type B) Nier:Automata - (1.5) v3.0](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/27dae7d5-5580-486e-b48d-f3f8c725af39/width=1024/3165721.jpeg)
Satoshi Urushihara Style - Urushisato V15 Readme
this is a huge 384 dim LoRA, experimenting with adaptive learning ratenote I tried resizing this LoRA to lower dims using the kohya_ss tools, but the quality results were too subjective (some images degrade, others are improved)training settings3137 training images512,512 training resolution16 epochs, 6,384 steps, 8 batchesnetwork dim & alpha 384DAdaptAdam optimizer, constant schedulerlearning rate 1.0bucketing & random cropuseful optional tokensurushisato tagged on all images for general style boostova tagged on all screencaps from animationbackground tagged on any image that has no human subject