Completed
26:12 Implementing our Wan 2.2 Comfyui Workflow
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Replacing Multiple Actors with Fine-Tuned Qwen and Wan 2.2
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 The Task: Generating Conan O’Brien interviewing Will Smith
- 2 2:04 Base Model Results and Early Fine-Tunes
- 3 3:13 The Problem: Video models aren’t good a multi person generations
- 4 6:50 Can we just prompt Nano Banana instead of fine-tuning
- 5 9:43 Why fine-tune?
- 6 11:17 What could a higher quality production pipeline look like?
- 7 14:50 Step 1: Masking
- 8 16:04 Enter DinoV3
- 9 21:28 Fine-tuning Qwen-Image-Edit to fill in masked images
- 10 26:12 Implementing our Wan 2.2 Comfyui Workflow
- 11 28:13 Questions
- 12 31:40 Tweaking our Comfyui flow
- 13 36:05 Moment of truth! Final generation
- 14 36:54 Question
- 15 38:15 Implementing our Qwen-Image-Edit LoRA in Comfyui
- 16 43:24 Conclusion
