Completed
0:00 Is it Wan like “Anne” or “won”?
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Training Video Generation with Wan 2.2 - Conan O'Brien and Will Smith Character Consistency
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Is it Wan like “Anne” or “won”?
- 2 0:55 The Wan suite of models
- 3 1:10 Wan 2.1’s model architecture and research paper
- 4 3:50 Wan 2.2 video improvements from Wan 2.1
- 5 5:35 Our fine-tuning goal: Conan O’Brien interviewing Will Smith who’s wearing a Denver Broncos shirt
- 6 7:30 Base model results
- 7 8:55 Wan 2.2’s model architecture
- 8 12:55 Fine-tuning: How we created our data
- 9 17:12 Fine-tuning: How we fine-tuned each Wan model
- 10 19:22 Question: How many images do you need?
- 11 20:24 Question: Did we use musubi-tuner?
- 12 20:40 Question: How to train camera panning
- 13 22:45 Fine-tuning: Comparing images as we fine-tune
- 14 29:37 Bringing our Will Smith fine-tuned model to Comfyui
- 15 42:00 Configuring Comfyui to run our fine-tuned model
- 16 47:28 Question: Does the image input format matter?
- 17 48:40 Loading our Conan O’Brien fine-tuned model on Comfyui
- 18 57:45 Question: How are the LoRAs loaded into the pipeline
- 19 58:40 Final Results: Conan interviewing Will Smith
