Deploy Dedicated GPU server to run AI models

Deploy Model
Skip to main content
LIPS - v1.0 thumbnail

LIPS - V1.0

by ModelsLab

Main training settings:7+7+12 epochs (The first two training sessions crashed after 8 epochs. Resumed the training from epoch 7 twice.)1 repeat per epochAdamW8bit optimizerLearning rates: U-Net=1e-5; TextEnc=2e-6Scheduler: Cosine with (restarts and) warmup for 10% of the stepsTrain batch size of 4No noise offset8997 imagesBase model: Luminaverse XL v1.0 + FixVAE v2Secondary training settings:25 epochs without crashing1 repeat per epochAdamW8bit optimizerLearning rates: U-Net=1e-6; TextEnc=0 (but no caching)Scheduler: Constant with no warmupTrain batch size of 4Noise offset: 0.03572317 images (a subset of the previous 8997)Base model: The output of the main training

lips-v1-0
Open Source ModelUnlimited UsageLLMs.txt
API PlaygroundAPI Documentation

Input

Select models...

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

View all Models
3D rendering style
Popular
ModelsLab

3D rendering style

Open Source Model
ouro_kronii_noobxl_eps_1.0 - v1.0
ModelsLab

ouro_kronii_noobxl_eps_1.0 - v1.0

Open Source Model
murakumo_(kancolle)_noobxl_eps_1.0 - v1.0
ModelsLab

murakumo_(kancolle)_noobxl_eps_1.0 - v1.0

Open Source Model
Thai Doll Arunee - SDXL 1.0
Popular
ModelsLab

Thai Doll Arunee - SDXL 1.0

Open Source Model
Experimental by Huggy - Gleam SDXL V01E06
Popular
ModelsLab

Experimental by Huggy - Gleam SDXL V01E06

Open Source Model
Cartoon Belka - V1
ModelsLab

Cartoon Belka - V1

Open Source Model
Alfa Romeo Tonale [SDXL] - v1.0
ModelsLab

Alfa Romeo Tonale [SDXL] - v1.0

Open Source Model
JJ's Japanese Garden - XL v1.0
Popular
ModelsLab

JJ's Japanese Garden - XL v1.0

Open Source Model
BASKET-PACK SDXL Medieval Style Backpack - V1
ModelsLab

BASKET-PACK SDXL Medieval Style Backpack - V1

Open Source Model
Radyanta Maristana (Rymyny) Character - SDXL V1.0 - v1.1
ModelsLab

Radyanta Maristana (Rymyny) Character - SDXL V1.0 - v1.1

Open Source Model
rabbit character v1
ModelsLab

rabbit character v1

Open Source Model
AI Model - Test - Character Test
ModelsLab

AI Model - Test - Character Test

Open Source Model
4th Tail LoRa extract - 0.2 M
Popular
ModelsLab

4th Tail LoRa extract - 0.2 M

Open Source Model
underground club - XL_1.0
Popular
ModelsLab

underground club - XL_1.0

Open Source Model
Image Enhancer XL - Medium v1
ModelsLab

Image Enhancer XL - Medium v1

Open Source Model
Kousaka Kirino (Pony,IL,XL,1.5) - v1.0-SDXL
Popular
ModelsLab

Kousaka Kirino (Pony,IL,XL,1.5) - v1.0-SDXL

Open Source Model
Anamorphic Bokeh + Special Effect (Shallow Depth of Field) cinematic style XL + F1D + SD1.5 - anamor
Popular
ModelsLab

Anamorphic Bokeh + Special Effect (Shallow Depth of Field) cinematic style XL + F1D + SD1.5 - anamor

Open Source Model
Win_Variation(umamusume)_XL & PONY & ILL - Animagine_v1.0
Popular
ModelsLab

Win_Variation(umamusume)_XL & PONY & ILL - Animagine_v1.0

Open Source Model

LIPS - V1.0 Readme

Main training settings:7+7+12 epochs (The first two training sessions crashed after 8 epochs. Resumed the training from epoch 7 twice.)1 repeat per epochAdamW8bit optimizerLearning rates: U-Net=1e-5; TextEnc=2e-6Scheduler: Cosine with (restarts and) warmup for 10% of the stepsTrain batch size of 4No noise offset8997 imagesBase model: Luminaverse XL v1.0 + FixVAE v2Secondary training settings:25 epochs without crashing1 repeat per epochAdamW8bit optimizerLearning rates: U-Net=1e-6; TextEnc=0 (but no caching)Scheduler: Constant with no warmupTrain batch size of 4Noise offset: 0.03572317 images (a subset of the previous 8997)Base model: The output of the main training