UrangDiffusion V3.1 - V1.2
by ModelsLabTraining 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-v1-2Input
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
![Kawaii Mirai | かわいい未来 (World Morph) [SDXL] - V1](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3047f2c5-ea54-44d9-add3-8863079ecc23/width=1024/85754336.jpeg)
![Object Showcase Collection of 60 Items [XL] - 53 Basketball Showcase](https://images.stablediffusionapi.com/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/86e2c422-4e65-4725-bf89-ec8cfab32943/width=1024/17730750.jpeg)
About UrangDiffusion V3.1 - V1.2
Training ConfigurationsFinetuned from: Animagine XL 3.1Pretraining:Dataset size: 23,500 imagesGPU: 1xA100 80GBOptimizer: AdaFactorUnet Learning Rate: 3.75e-6Text Encoder Learning Rate: 1.875e-6Batch Size: 48Gradient Accumulation: 1Warmup steps: 100 stepsMin SNR: 5Epoch: 10 (epoch 9 is used)Finetuning:Dataset size: 6,800 imagesGPU: 1xA100 80GBOptimizer: AdaFactorUnet Learning Rate: 2e-6Text Encoder Learning Rate: - (Train TE set to False)Batch Size: 48Gradient Accumulation: 1Warmup steps: 5%Min S
Technical Specifications
- Model ID
- urangdiffusion-v3-1-v1-2
- Provider
- Modelslab
- Task
- AI Generation
- Price
- $0.0047 per API call
- Added
- June 4, 2025
Quick Start
Integrate UrangDiffusion V3.1 - V1.2 into your application with a single API call. Get your API key from the pricing page to get started.
import requestsimport jsonurl = "https://modelslab.com/api/v6/images/text2img"headers = {"Content-Type": "application/json"}data = {"model_id": "urangdiffusion-v3-1-v1-2","prompt": "your prompt here","key": "YOUR_API_KEY"}try:response = requests.post(url, headers=headers, json=data)response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX)result = response.json()print("API Response:")print(json.dumps(result, indent=2))except requests.exceptions.HTTPError as http_err:print(f"HTTP error occurred: {http_err} - {response.text}")except Exception as err:print(f"Other error occurred: {err}")
View the full API documentation for SDKs, code examples in Python, JavaScript, and more.
Pricing
UrangDiffusion V3.1 - V1.2 API costs $0.0047 per API call. Pay only for what you use with no minimum commitments. View pricing plans
UrangDiffusion V3.1 - V1.2 FAQ
Training ConfigurationsFinetuned from: Animagine XL 3.1Pretraining:Dataset size: ~23,500 imagesGPU: 1xA100 80GBOptimizer: AdaFactorUnet Learning Rate: 3.75e-6Text Encoder Learning Rate: 1.875e-6Batch Size: 48Gradient Accumulation: 1Warmup steps: 100 stepsMin SNR: 5Epoch: 10 (epoch 9 is used)Finetuni
You can integrate UrangDiffusion V3.1 - V1.2 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "urangdiffusion-v3-1-v1-2" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation.
UrangDiffusion V3.1 - V1.2 costs $0.0047 per API call. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started.
The model ID for UrangDiffusion V3.1 - V1.2 is "urangdiffusion-v3-1-v1-2". Use this ID in your API requests to specify this model.
Yes, ModelsLab offers a free tier that lets you try UrangDiffusion V3.1 - V1.2 and other AI models. Sign up to get free API credits and start building immediately.