My first try at a WAN Celebrity lora and it works very well, much better than I expected.
Trained on Wan2.1-T2V-14B
Works both for T2V and for I2V.
Other Versions:
Pony version
SDXL version
SD 1.5 version
🙏 If you like this model, please click the Like button and post some pictures, it really helps for visibility! 🙏
You can now request a custom LoRa on 👉Ko-Fi (No charges)👈 or 👉 Fiverr 👈
Description
FAQ
Comments (7)
Goated
Thanks a lot! Great quality LoRA! Hope you’ll keep uploading more busty girl models like this.
Nice lora! Do you mind sharing what parameters you used for training the lora, is it on images only or movie clips as well? I trained a character lora with images only but the video gets distorted when combining with other loras, it's only ok by itself, yours seemed to combine well with others to a better degree
Thank you ! I used this guide: https://learn2train.medium.com/fine-tuning-wan-2-1-with-a-curated-dataset-step-by-step-guide-a6f0b334ab79
Amazing work on your Lucie Wilde LoRA for Wan2.1 T2V 14B! I saw you achieved great results
I'd love to learn from your experience as I'm training a similar LoRA on my RTX 4090 (24GB) using Diffusion-Pipe.
Could you possibly share some specifics of your training config? I'm trying to figure out the optimal settings, especially:
What resolution did you train at?
What LoRA rank did you use (to get the ~300MB size)?
What optimizer (e.g., AdamW8bitKahan?), lr, and LR scheduler settings worked well?
Roughly how many epochs did you train for?
What did you set for gradient_accumulation_steps and num_repeats in the dataset config?
Did you need to use blocks_to_swap, and if so, how many? Was activation_checkpointing enabled?
For captions, did you use detailed descriptions or just a trigger word?
Understanding these key parameters would be a massive help. Thanks for considering!