Updated to Wan 2.2
Rapunzel from Tangled
"Rapunzel" is the trigger.
Very important! Start your prompt with "3D Cartoon Style", unless using another style lora
Movie outfit
She is wearing a purple Dress with puffy sleeves, barefootMovie Hairstyles
Very long flowing golden blonde hairVery long golden blonde hair braided with colorful flowersShort tousled brown hair"Green chameleon" for Pascal
Use both Low and High noise loras.
All preview videos made with Wan 2.2 lightx2v lora on Q8. Comfyui workflows embedded in videos
Expect poor results with 2.1 lightx2v. I use the official Wan 2.2 lightx2v lora found here: https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1.1
Not tested extensively with other 2.2 loras but should work okay, adjust strength as necessary
Description
FAQ
Comments (9)
😻💕👍🏻
I love this, the only thing is that its hard to get her outfit to change from the original one or to remove any parts of the clothes
Hi, could you share the training details/configs for training this lora? I trained a lora for a 3D character, but the resulting quality is not satisfactory. The character model seems to have lower polygon and the motion is stiff.
@Kong__ what learning rate did you use?
I can't get this LORA to work no matter what I try. I either end up with a photorealistic person or something that looks like a polygonal mess. Does this only work with a specific diffusion model?
Should work with any 14b T2V model. I tested both Q8 Comfy nodes and fp8 on KJ nodes. You need to include CGI somewhere in your prompt, easiest is to start your prompt with "CGI scene of"
@Kong__ Yeah even when the prompt starts with "CGI scene of" it still looks terrible.
@TurkeyCannon I'm not sure then, are you using the 1.3b model? I've added workflows to the description perhaps they can help.
@TurkeyCannon What’s your exact prompt, Lora strengths, and step count? I’ve tried 0.7-1.0 and 40-50 steps and works well. No lightx2v and detailed prompt
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.