harryfrz/sakura-sd-v1.5

🌸 Sakura-diffusion-v1.5

Sakura-diffusion-v1.5 is a LoRA fine-tuning of Stable Diffusion v1.5 to generate high-quality anime-style images. The model was trained on a Google Colab T4 GPU (free tier), so there were some training and dataset size constraints. With more resources, it could be trained on a larger dataset for even better performance. For this version, the Dhiraj45/AnimeStyle dataset was used for fine-tuning. Despite the limitations, the model produces strong and visually pleasing anime-style results at most times

<img src="https://cdn-uploads.huggingface.co/production/uploads/685d7f0d0099df74d3b3b5d4/ppg48m6MtxJ0Q-DB09lG2.png" width="500"/> <img src="https://cdn-uploads.huggingface.co/production/uploads/685d7f0d0099df74d3b3b5d4/MSXnSC7uAylm2JkuuQR.png" width="500"/>

✨ Try the model

You can try out the model by clicking the Use the model button, then selecting the Colab notebook from the dropdown menu to run the model directly in your own Colab instance.

Trigger words

• —You should use anime style to trigger the image generation.
• —You should use anime art to trigger the image generation.
• —You should use anime art style to trigger the image generation.

Download model

Download them in the Files & versions tab.