UrangDiffusion V3.1 - V3.1
by ModelsLabUrangDiffusion XL v3.1 is fine-tuned from Animagine XL 4.0 Base (not Zero). This 4.0 Base model serves as the base model pre-trained for the final release of Animagine XL 4.0 (not the Opt version).
I have received permission from the team to fine-tune the base model using my own method and release it under the UrangDiffusion series.
Base model: Animagine XL 4.0 Base
Fine-tuning details:
Dataset size: ~1,600 images
GPU: 1× A100 80GB
Optimizer: AdaFactor
UNet learning rate: 1.25e-6
Text encoder learning rate: N/A (disabled)
Batch size: 48
Gradient accumulation: 1
Warmup steps: 5%
Minimum SNR: 5
Epochs: 15
Due to some quirks of the model, please keep the following in mind:
v3.0 may perform better with anatomy
v3.1 may perform better with more fluid poses
If you encounter anatomical issues at 28 steps, try lowering to 27 or increasing to 29. If it improves but isn’t perfect, continue adjusting slightly up or down. If the result worsens, the previous step count was likely the optimal one.
UPDATE [19/04/2025]
Some generations are stable at step 30++ with Euler a. You might wanna crank up the steps a bit.
Some generations are also better with
realistic, 3dincluded in the negative. Try that too.
urangdiffusion-v3-1-v3-1Input
Output
Unknown content type
Looking for something different?
Models that trade off differently against the one you are viewing
Better quality
Newer flagship models that generally produce stronger results.
Faster Generation
Built for speed when you are iterating on a prompt.
Related Models
Discover similar models you might be interested in
![Psychedelic Dream [SDXL / FLUX] - SDXL v1.0](https://images.modelslab.sh/?Image=https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ab507a0e-0d20-445d-9a87-6dcd67b2b477/width=832/87982572.jpeg)
About UrangDiffusion V3.1 - V3.1
UrangDiffusion XL v3.1 is fine-tuned from Animagine XL 4.0 Base (not Zero). This 4.0 Base model serves as the base model pre-trained for the final release of Animagine XL 4.0 (not the Opt version).I have received permission from the team to fine-tune the base model using my own method and release it under the UrangDiffusion series.Base model: Animagine XL 4.0 BaseFine-tuning details:Dataset size: 1,600 imagesGPU: 1× A100 80GBOptimizer: AdaFactorUNet learning rate: 1.25e-6Text encoder learning ra
Technical Specifications
- Model ID
- urangdiffusion-v3-1-v3-1
- Provider
- ModelsLab
- Task
- AI Generation
- Price
- $0.0047 per API call
- Added
- June 4, 2025
Quick Start
Integrate UrangDiffusion V3.1 - V3.1 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-v3-1","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}")
Pricing
UrangDiffusion V3.1 - V3.1 API costs $0.0047 per API call. Plans start at $21/month, and open-source models are unlimited on the $149/month plan. View pricing plans