HyHorX/realistic-diffusion-v2

HyHorX/realistic-diffusion-v2: A state-of-the-art model for photorealistic tasks.

Realistic Diffusion v2 is an advanced model optimized to generate lifelike imagery. By leveraging a vast dataset of prompts, it strikes a perfect balance between exceptional speed and high-fidelity quality.

Training info

Training method: Knowledge distillation
Number of steps: 15,000
Learning rate: 2e-5
Trained on: x2 T4 GPU
Each GPU's batch size: 4
Gradient Accumulation: 4
Total batch size: 32 (4 x 2 x 4)

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here

Downstream Uses

This model can be used for entertainment purposes and as a generative art assistant.