Fine Tuning Video Generation Models | Make Your Own AI Videos
Training video models with… Images? Turns out video diffusion and image diffusion is similar enough that we can train the latest open source video generation models with a limited number of labeled images.
Resources:
Model Trained: https://huggingface.co/AdamLucek/Wan2.1-T2V-14B-OldBookIllustrations
Written Blog Tutorial: https://learn2train.medium.com/fine-tuning-wan-2-1-with-a-curated-dataset-step-by-step-guide-a6f0b334ab79
Video Diffusion Blog: https://lilianweng.github.io/posts/2024-04-12-diffusion-video/#adapting-image-models-to-generate-videos
Diffusion Pipe: https://github.com/tdrussell/diffusion-pipe
ComfyUI: https://github.com/comfyanonymous/ComfyUI
Wan Paper: https://arxiv.org/pdf/2503.20314
Wan2.1-T2V-14B: https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
Chapters:
00:00 - Introduction
00:34 - How Video Generation Works
06:40 - Training: Dataset Preparation
11:42 - Training: Environment Setup
18:28 - Training: Configuration
23:38 - Training: Testing the Models
#ai #datascience #finetuning
Видео Fine Tuning Video Generation Models | Make Your Own AI Videos канала Adam Lucek
Resources:
Model Trained: https://huggingface.co/AdamLucek/Wan2.1-T2V-14B-OldBookIllustrations
Written Blog Tutorial: https://learn2train.medium.com/fine-tuning-wan-2-1-with-a-curated-dataset-step-by-step-guide-a6f0b334ab79
Video Diffusion Blog: https://lilianweng.github.io/posts/2024-04-12-diffusion-video/#adapting-image-models-to-generate-videos
Diffusion Pipe: https://github.com/tdrussell/diffusion-pipe
ComfyUI: https://github.com/comfyanonymous/ComfyUI
Wan Paper: https://arxiv.org/pdf/2503.20314
Wan2.1-T2V-14B: https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
Chapters:
00:00 - Introduction
00:34 - How Video Generation Works
06:40 - Training: Dataset Preparation
11:42 - Training: Environment Setup
18:28 - Training: Configuration
23:38 - Training: Testing the Models
#ai #datascience #finetuning
Видео Fine Tuning Video Generation Models | Make Your Own AI Videos канала Adam Lucek
artificial intelligence OpenAI AI Gemini Llama Open Source HuggingFace Machine Learning Deep Learning AI Trends AI Applications AI Tutorial AI Research AI Solutions AI Software AI Algorithms Artificial General Intelligence AI Strategy AI Integration Multimodal Agent LangChain gpt-4o gpt langsmith fine-tuning RAG data synthetic Learning llm retrieval neural o3 reasoning o1 test time compute deepseek MCP model context protocol sora wan huyuan video AI videos
Комментарии отсутствуют
Информация о видео
4 апреля 2025 г. 17:01:03
00:30:48
Другие видео канала
How To Summarize & Chunk Technical Documents with AI Language Models
How AI Creates Images/Videos/Audio - Diffusion Models Explained
Building a Thinking Machine: My Gemma 2 9B Reflection Agent
Why Every AI Developer Should Learn Model Context Protocol (MCP)
Fine Tuning OpenAI Models Walkthrough - How and Why
Model Output Comparison with GPT/Gemini/Mistral/Llama2 - PulseRead Followup
Making YouTube Videos With AI! - How to Use LLM & ATT Models to Make Engaging Content
LLM Model Output Comparison - Mistral Large/Gemma 7b/Llama 70b/Claude 3 Opus & More Pt.2
Master Reinforcement Learning With These 3 Projects
Large Multimodal Models Are The Future - Text/Vision/Audio in LLMs
How To Easily Run & Use LLMs Locally - Ollama & LangChain Integration
Improving RAG Retrieval by 60% with Fine-Tuned Embeddings
Build Your Own Finance LLM for FREE with SEC Data
Does Fine Tuning Embedding Models Improve RAG?
Quantizing LLMs - How & Why (8-Bit, 4-Bit, GGUF & More)
BERT: The Most Used AI Model You Haven't Heard Of
Stop Prompt Engineering! Program Your LLMs with DSPy
Breaking Down & Testing FIVE LLM Agent Architectures - (Reflexion, LATs, P&E, ReWOO, LLMCompiler)
The BEST Way to Chunk Text for RAG
Multimodal RAG!? - Pushing the Boundaries of AI
I Trained an LLM to Think Deeper (Here's How)