Watch and track your favorite playlist.
Curated by: VictoryCat (71 videos)
In this video we go over how we can use the Wan 2.2 video generation model within ComfyUI. Timeline: 0:00 - Intro 0:51 - Where to get the workflows 1:21 - Where to put the model files 3:26 - Running the workflows 3:50 - Single Image Workflow 12:25 - First Frame Last Frame Workflow 16:36 - Video Extension Workflow 16:45 - Downloading KJ nodes 20:34 - Closing The github repository for our workflows can be found here: https://github.com/VictoryCATiii3/ComfyUI-Workflows/tree/main/ForWan If you want to see how to set this up on runpod (cloud based computing if you don't have a local GPU): https://youtu.be/SrJgqdKmXkQ If you want to see how we add ComfyUI Manager to ComfyUI so we can add custom nodes: https://youtu.be/5FsA6-OET5c To download the files that are necessary to run this workflow, go to: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files The files may also be downloaded from the links in the note on the left side of the workflow. The exact files and locations where they need to be put are as follows: From Diffusion models: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models we need: wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors in our ComfyUI/models/diffusion_models folder. From LoRAs: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/loras we need: wan2.2_i2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors wan2.2_i2v_lightx2v_4steps_lora_v1.1_low_noise.safetensors in our ComfyUI/models/loras folder From VAE: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/vae We need: wan_2.1_vae.safetensors In our ComfyUI/models/vae folder From Text Encoders: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/text_encoders We need: umt5_xxl_fp8_e4m3fn_scaled.safetensors In our ComfyUI/models/text_encoders folder. #tutorial #aivideogeneration #wanvideo #comfyui #videocontrol