Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗

App herunterladen

Ditto GGUF | ST Studio

Readme3. Aug.huggingface.co/vantagewithai/Ditto-GGUF

--- base_model: - Wan-AI/Wan2.1-T2V-14B - Wan-AI/Wan2.1-VACE-14B datasets: - QingyanBai/Ditto-1M language: - en license: cc-by-nc-sa-4.0 pipeline_tag: video-to-video --- # GGUF Quantized versions of Ditto Models **Original model link:** [QingyanBai/Ditto_models](https://huggingface.co/QingyanBai/Ditto_models) **Watch us at Youtube:** [@VantageWithAI](https://www.youtube.com/@vantagewithai) # Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset This repository contains the **Ditto** framework and the **Editto** model, which are introduced in the paper [Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset](https://huggingface.co/papers/2510.15742). Ditto provides a holistic approach to address the scarcity of high-quality training data for instruction-based video editing, enabling the creation of the Ditto-1M dataset and the training of the state-of-the-art Editto model. - 📄 [Paper](https://huggingface.co/papers/2510.15742) - 🌐 [Project Page](https://ezioby.github.io/Ditto_page) - 💻 [GitHub Repository](https://github.com/EzioBy/Ditto) - 📦 [Model Weights (on HF)](https://huggingface.co/QingyanBai/Ditto_models/tree/main) - 📊 [Dataset (on HF)](https://huggingface.co/datasets/QingyanBai/Ditto-1M) ## Abstract Instruction-based video editing promises to democratize content creation, yet its progress is severely hampered by the scarcity of large-scale, high-quality training data. We introduce Ditto, a holistic framework designed to tackle this fundamental challenge. At its heart, Ditto features a novel data generation pipeline that fuses the creative diversity of a leading image editor with an in-context video generator, overcoming the limited scope of existing models. To make this process viable, our framework resolves the prohibitive cost-quality trade-off by employing an efficient, distilled model architecture augmented by a temporal enhancer, which simultaneously reduces computational overhead and improves temporal coherence. Finally, to achieve full scalability, this entire pipeline is driven by an intelligent agent that crafts diverse instructions and rigorously filters the output, ensuring quality control at scale. Using this framework, we invested over 12,000 GPU-days to build Ditto-1M, a new dataset of one million high-fidelity video editing examples. We trained our model, Editto, on Dit...