--- license: creativeml-openrail-m language: - en library_name: diffusers pipeline_tag: text-to-image tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image inference: parameters: num_inference_steps: 50 guidance_scale: 5.0 eta: 1.0 --- # ddpo-aesthetic This model was finetuned from [Stable Diffusion v1-5](https:/runwayml/stable-diffusion-v1-5) using [DDPO](https://arxiv.org/abs/2305.13301) using the [LAION aesthetic predictor](https://laion.ai/blog/laion-aesthetics/) as a reward function. It was finetuned for 50 iterations with a batch size of 256 samples per iteration.