2d Art Sprites

🚀 2d-art-sprites Dreambooth Model

This is a 2d-art-sprites Dreambooth model trained by ana-tamais, which can generate text-to-image results in a specific 2d art style.

🚀 Quick Start

You can test this model using this Colab Notebook for Inference.

Sample Pictures

Sample pictures of 2dart concept:

We saved the training data in dataset.zip, and some generated results in results.zip.

💡 Usage Tips

📋 Hyperparameters Recommendation

We recommend to set the following hyperparameters:

• Prompt: "[some wizard, paladin, healer, etc.], in the style of 2dart, white background, no background, full body"
• Negative Prompt: "deformed, mutilated limbs, background, multiple people"
• Guidance Scale: between 9 and 10
• Sampling Method: Euler
• Sampling Steps: 60
• Batch Size: 1 - avoid high batch size, unless you have a high memory GPU

This set of hyperparameters lead us to stable and good results.

⚠️ Important Note

This model was trained using images which the character has some human format or is a not deformed living being. So if you try to predict something like "sword, mirror, candle, etc" (non-living things), we saw the model doesn't perform so well.

You need at least a Tesla T4 to be able to run the inference step using the given notebook.

📄 License

The model is under the creativeml-openrail-m license.

📦 Model Information