Oxen Courses

100% AI Car Commercial - Behind the Scenes of the Entire Process

Discover the complete technical workflow behind creating a fully AI-generated car commercial, from initial concept to final production with industry experts.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

Replacing Multiple Actors with Fine-Tuned Qwen and Wan 2.2

Discover how to fine-tune Qwen and Wan 2.2 models to generate multi-person video content, overcoming limitations in AI video generation through advanced masking and workflow techniques.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Fine-Tuning Wan 2.1 VACE to Swap Costumes

Master fine-tuning Wan 2.1 VACE model to seamlessly swap actor costumes in post-production using LoRA training, ComfyUI workflows, and professional video editing techniques.

• YouTube
• 53 minutes
• Self-Paced
• Free Video

Fine-Tuning Qwen-Image-Edit-2509 on Nike Clothing and Poses

Master fine-tuning Qwen-Image-Edit-2509 for Nike product catalogs, from dataset preparation and auto-captioning to training optimization and results comparison.

• YouTube
• 25 minutes
• Self-Paced
• Free Video

Fine-Tuned Qwen-Image-Edit vs Nano-Banana - Generating 1.2 Million Images

Discover how to fine-tune Qwen-Image-Edit for generating 1.2M images while cutting inference costs, comparing performance with Nano-Banana for furniture color variations.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

How a $1 Qwen3-VL Fine-Tune Beat Gemini 3

Discover how to fine-tune Qwen3-VL for just $1 and outperform Gemini 3 in vision-language tasks through practical demonstrations and cost-effective AI model optimization techniques.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Training LTX-2 - How to Fine-tune a LoRA for Character Consistency

Master fine-tuning LTX-2 video generation model with LoRA techniques for consistent character representation using Yoda as a test case in this hands-on tutorial.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

How to Fine-Tune FLUX-dev and Comparing it to a Fine-Tuned PixArt Model

Master FLUX-dev fine-tuning with LoRA techniques, data requirements, hardware setup, and code walkthrough. Compare results against PixArt models for optimal AI image generation.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

We Fine-Tuned GPT OSS 20B to Rap Like Eminem

Discover how to fine-tune GPT OSS 20B models to rap like Eminem, covering data handling, automation, model internals, attention mechanisms, and deployment strategies.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Fine-Tuning a Diffusion Transformer to Generate OpenAI Level Images

Master fine-tuning diffusion transformers to create high-quality AI images using synthetic data generation and advanced training techniques for professional results.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Fine-Tuning a Tab Tab Code Completion Model

Discover how to fine-tune AI models for intelligent code completion, building Cursor-like "tab tab" functionality with practical examples and model comparisons.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Training Video Generation with Wan 2.2 - Conan O'Brien and Will Smith Character Consistency

Master video generation with Wan 2.2 by fine-tuning models for character consistency using Conan O'Brien and Will Smith examples, covering architecture, data creation, and ComfyUI integration.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Fine-Tuned Qwen-Image-Edit vs Nano-Banana and FLUX.1 Kontext

Explore fine-tuning Qwen-Image-Edit against Nano-Banana and FLUX.1 Kontext models through practical comparisons and hands-on training demonstrations for image editing tasks.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

How Vision Language Models Reason - Understanding LLaVa Chain of Thought

Delve into the technical aspects of LLaVa-CoT's vision language models, exploring data generation, training methodologies, and inference-time scaling for enhanced reasoning capabilities.

• YouTube
• 37 minutes
• Self-Paced
• Free Video

RAGAS - A Framework for Evaluating Retrieval Augmented Generation Systems

Explore RAGAS framework's key evaluation criteria for Retrieval Augmented Generation (RAG) systems, covering faithfulness, answer relevance, and context relevance metrics for improved AI performance.

• YouTube
• 43 minutes
• Self-Paced
• Free Video