Deploy Dedicated GPU server to run AI models

Deploy Model
Skip to main content
UrangDiffusion v3.1 - v1.2 thumbnail

UrangDiffusion V3.1 - V1.2

by ModelsLab

Training Configurations

Finetuned from: Animagine XL 3.1

Pretraining:

  • Dataset size: ~23,500 images

  • GPU: 1xA100 80GB

  • Optimizer: AdaFactor

  • Unet Learning Rate: 3.75e-6

  • Text Encoder Learning Rate: 1.875e-6

  • Batch Size: 48

  • Gradient Accumulation: 1

  • Warmup steps: 100 steps

  • Min SNR: 5

  • Epoch: 10 (epoch 9 is used)

Finetuning:

  • Dataset size: ~6,800 images

  • GPU: 1xA100 80GB

  • Optimizer: AdaFactor

  • Unet Learning Rate: 2e-6

  • Text Encoder Learning Rate: - (Train TE set to False)

  • Batch Size: 48

  • Gradient Accumulation: 1

  • Warmup steps: 5%

  • Min SNR: 5

  • Epoch: 10

  • Noise Offset: 0.0357

Wuthering Waves, Zenless Zone Zero and hololiveEN -Justice- have been added to the model.

urangdiffusion-v3-1-v1-2
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
FENGLI - V1
ModelsLab

FENGLI - V1

Open Source Model
Lovely style | - v1.1
ModelsLab

Lovely style | - v1.1

Open Source Model
In The Shoe Locker ( )IL SDXL - SDXL
ModelsLab

In The Shoe Locker ( )IL SDXL - SDXL

Open Source Model
JJ's Interior Space - Bedroom - XL v1.0
Popular
ModelsLab

JJ's Interior Space - Bedroom - XL v1.0

Open Source Model
Restoration of hand models for two-dimensional characters - v1.0
ModelsLab

Restoration of hand models for two-dimensional characters - v1.0

Open Source Model
CUE! Characters - XL Utsugi Satori
Popular
ModelsLab

CUE! Characters - XL Utsugi Satori

Open Source Model
Spider-Man (Peter B. Parker) from Into the Spider-Verse [LoRA] - v1.0 SDXL
Popular
ModelsLab

Spider-Man (Peter B. Parker) from Into the Spider-Verse [LoRA] - v1.0 SDXL

Open Source Model
Astigmatism (formerly 'Semantic Shift') - Astigmatism +0.6
Popular
ModelsLab

Astigmatism (formerly 'Semantic Shift') - Astigmatism +0.6

Open Source Model
[Flux/SDXL] - Black Diamonds - SDXL
ModelsLab

[Flux/SDXL] - Black Diamonds - SDXL

Open Source Model
DynaVision
Popular
ModelsLab

DynaVision

Open Source Model
Azur Lane Meta Style - v1.0 Anything XL
ModelsLab

Azur Lane Meta Style - v1.0 Anything XL

Open Source Model
Kohaku-XL beta - beta7
Popular
ModelsLab

Kohaku-XL beta - beta7

Open Source Model
Guns (Lots Of Guns) XL + F1D (Choose from list) - Heckler & Koch MP5 v1.0
Popular
ModelsLab

Guns (Lots Of Guns) XL + F1D (Choose from list) - Heckler & Koch MP5 v1.0

Open Source Model
samaritan_3d_cartoon_sdxl
ModelsLab

samaritan_3d_cartoon_sdxl

Open Source Model
warrior_of_light_(ff14)_noobxl_eps_1.0 - v1.0
ModelsLab

warrior_of_light_(ff14)_noobxl_eps_1.0 - v1.0

Open Source Model
Detailers By Stable Yogi - Super_Eye_Detailer_XL_PNY
Popular
ModelsLab

Detailers By Stable Yogi - Super_Eye_Detailer_XL_PNY

Open Source Model
Shoe Locker (getabako) IL SDXL - SDXL
ModelsLab

Shoe Locker (getabako) IL SDXL - SDXL

Open Source Model
akaboshi_koume_noobxl_eps_1.0 - v1.0
ModelsLab

akaboshi_koume_noobxl_eps_1.0 - v1.0

Open Source Model

UrangDiffusion V3.1 - V1.2 Readme

Training Configurations

Finetuned from: Animagine XL 3.1

Pretraining:

  • Dataset size: ~23,500 images

  • GPU: 1xA100 80GB

  • Optimizer: AdaFactor

  • Unet Learning Rate: 3.75e-6

  • Text Encoder Learning Rate: 1.875e-6

  • Batch Size: 48

  • Gradient Accumulation: 1

  • Warmup steps: 100 steps

  • Min SNR: 5

  • Epoch: 10 (epoch 9 is used)

Finetuning:

  • Dataset size: ~6,800 images

  • GPU: 1xA100 80GB

  • Optimizer: AdaFactor

  • Unet Learning Rate: 2e-6

  • Text Encoder Learning Rate: - (Train TE set to False)

  • Batch Size: 48

  • Gradient Accumulation: 1

  • Warmup steps: 5%

  • Min SNR: 5

  • Epoch: 10

  • Noise Offset: 0.0357

Wuthering Waves, Zenless Zone Zero and hololiveEN -Justice- have been added to the model.