ATTENTION! This is my second Wan 2.2 LoRA and is mainly for testing and sharing ideas about training a Wan2.2 LoRA. Please let me know if you have any experience on training Wan2.2 LoRA.
VioletEvergardenStyle-Wan2.2-T2V-A14B. You can use MediaInfo to check the generation info in the video. The workflow I used is the official one but adding sage attention and LoRAs after loading the ckpt.
If you love my work, you can buy me a coffee : https://ko-fi.com/ghostshell
UPDATE VERSION-2.0
The effect I tested is crazy. Sample videos are generated in [720,960] or [1024,1536].
wan22-style1-violetevergarden-16-sel-2-high-000100.safetensors is for high noise
wan22-style1-violetevergarden-16-sel-2-low-4-000060.safetensors is for low noise
The Image below contains the Workflow.
VERSION-1.0
wan22-style1-violetevergarden-16-sel-2-high-000100.safetensors is for high noise
wan22-style1-violetevergarden-16-sel-2-low-3-000080.safetensors is for low noise
Description
train in a higher latent resolution
FAQ
Comments (2)
If only I knew how to do this and had a GPU above 1060, I'd help as best I could in the ideation stage :( BUT love your progress! I really do have high hopes of this being a true success!
Thank you!