# This CITATION.cff file was generated with cffinit. # Visit https://bit.ly/cffinit to generate yours today! cff-version: 1.2.0 title: Hotshot-XL message: Personalized GIF Generation with Diffusion Models type: software authors: - given-names: John family-names: Mullan email: john@codename.app affiliation: 'Natural Synthetics, Inc.' - given-names: Duncan family-names: Crawbuck email: duncan@codename.app affiliation: 'Natural Synthetics, Inc.' - given-names: Aakash family-names: Sastry email: aakash@codename.app affiliation: 'Natural Synthetics, Inc.' identifiers: - type: url value: 'https://hotshot.co' description: Hotshot Website repository-code: 'https://github.com/hotshotco/hotshot-xl' url: 'https://hotshot.co' repository-artifact: 'https://huggingface.co/hotshotco/Hotshot-XL' abstract: >- Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL. Hotshot-XL can generate GIFs with any fine-tuned SDXL model. Hotshot-XL is able to make GIFs with any existing or newly fine-tuned SDXL model you may want to use. If you'd like to make GIFs of personalized subjects, you can load your own SDXL based LORAs, and not have to worry about fine-tuning Hotshot-XL. This is awesome because it’s usually much easier to find suitable images for training data than it is to find videos. Hotshot-XL is compatible with SDXL ControlNet to make GIFs in the composition/layout you’d like. Hotshot-XL was trained to generate 1 second GIFs at 8 FPS. Hotshot-XL was trained on various aspect ratios. To achieve more efficient training + inference, we fine tuned SDXL at/around 512 resolution prior to training Hotshot-XL. We also publish our fine tuned SDXL spatial model for use among the research community. keywords: - ai - text-to-video - sdxl - text-to-video-generation - text-to-gif - hotshot-xl - hotshot license: Apache-2.0 commit: 16f99c4e8cbf8cebd038a282173767d609836889 version: 1.0.0 date-released: '2023-10-03'