Ditto, a free and open-source AI that can edit videos using text prompts.Developed by Ant Group, an affiliate of Alibaba, Ditto is a holistic framework designed for instruction-based video editing. It utilizes a novel data generation pipeline to create a large-scale, high-quality dataset of video editing examples.Tested on 10GB GPU + 64GB RAM + 'Sage Attention' , 3 120GHZ monitors, Firefox (21 Tabs open 4 actively used) , background music , Ubuntu 24.04.3 LTS: works like a charmBase model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1651125?modelVersionId=1868891">https://civarchive.com/models/1651125?modelVersionId=1868891</a> or any wan2.1 T2V (Text to video)<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan21_CausVid_14B_T2V_lora_rank32_v2.safetensors">Wan21_CausVid_14B_T2V_lora_rank32_v2.safetensors</a> to <code>loras/</code> for inference acceleration</li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors">Wan2_1_VAE_bf16.safetensors</a> to <code>vae/wan/</code></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/blob/main/umt5-xxl-enc-bf16.safetensors">umt5-xxl-enc-bf16.safetensors</a> to <code>text_encoders/</code> fp8 is not supported yet</li></ul>Workflow in training data file or search civitai for different variations More info <a target="_blank" rel="ugc" href="https://huggingface.co/QingyanBai/Ditto_models">HuggingFace</a> | <a target="_blank" rel="ugc" href="https://github.com/EzioBy/Ditto?tab=readme-ov-file">GitHub</a>These models are redistributed here for the sake of convenience.

Files with SHA256: ad89c2871a616bba6ab66d85331c449b8c84e8d946c0342e0de9e3822fdc49fb