¿Tienes un flujo de trabajo de ComfyUI? Obtén un Workflow Doc legible en tu navegador.Haz legible un flujo de trabajo.Pruébalo ahora ↗
Watch us at Youtube: @VantageWithAI
Fuente del modelo
Extracto de la fuente
Watch us at Youtube: @VantageWithAI
Fuentes
1 fuenteVerificado 3 ago
Artefactos del modelo
36 artefactosExtractos de fuentes
2 extractosglobal-style/ditto_global_style_Q4_0.gguf
gguf · 1,64 GB · SHA-256 ae21f978ee1e…439f · Hugging Face
Descargarglobal-style/ditto_global_style_Q4_1.gguf
gguf · 1,78 GB · SHA-256 d11f2719eea7…ae14 · Hugging Face
Descargarglobal-style/ditto_global_style_Q4_K_M.gguf
gguf · 1,84 GB · SHA-256 4b0d6a9c8dd8…bbec · Hugging Face
Descargarglobal-style/ditto_global_style_Q4_K_S.gguf
gguf · 1,69 GB · SHA-256 236fd4c4b4e2…0693 · Hugging Face
Descargarglobal-style/ditto_global_style_Q5_0.gguf
gguf · 1,99 GB · SHA-256 c3def3b2c97e…3e39 · Hugging Face
Descargarglobal-style/ditto_global_style_Q5_1.gguf
gguf · 2,14 GB · SHA-256 129a165d9e09…a6be · Hugging Face
Descargarglobal-style/ditto_global_style_Q5_K_M.gguf
gguf · 2,08 GB · SHA-256 108ba0d3541e…ea86 · Hugging Face
Descargarglobal-style/ditto_global_style_Q5_K_S.gguf
gguf · 1,96 GB · SHA-256 e8162927b69b…941f · Hugging Face
Descargarglobal-style/ditto_global_style_Q6_K.gguf
gguf · 2,34 GB · SHA-256 bccb7f8555e6…3ae4 · Hugging Face
Descargarglobal-style/ditto_global_style_Q8_0.gguf
gguf · 3,03 GB · SHA-256 4cf8d91dedeb…f32b · Hugging Face
Descargarsim2real/ditto_sim2real_Q3_K_M.gguf
gguf · 1,36 GB · SHA-256 5c52ce0c5e01…268c · Hugging Face
Descargarsim2real/ditto_sim2real_Q3_K_S.gguf
gguf · 1,23 GB · SHA-256 bf6b958d85e8…b773 · Hugging Face
Descargarsim2real/ditto_sim2real_Q4_K_M.gguf
gguf · 1,84 GB · SHA-256 7cc5820223dc…e28b · Hugging Face
Descargarsim2real/ditto_sim2real_Q4_K_S.gguf
gguf · 1,69 GB · SHA-256 0c705c87ee30…b219 · Hugging Face
Descargarsim2real/ditto_sim2real_Q5_K_M.gguf
gguf · 2,08 GB · SHA-256 def8755682e4…9a38 · Hugging Face
Descargarsim2real/ditto_sim2real_Q5_K_S.gguf
gguf · 1,96 GB · SHA-256 496ab0430a41…2366 · Hugging Face
Descargar--- 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...
Source context: 283 downloads · 2 likes · Pipeline video-to-video · Repo vantagewithai/Ditto-GGUF
