Blackedraw Style — Doggy Style is an LoRA designed for MiniMax H3 Ref2VA
Designed primarily for reference-to-video workflows, with an emphasis on maintaining the intended pose while allowing flexibility in character appearance
Update 1.1 Showcase ✨ NEW
Version 1.1 includes:
3× larger dataset
Pronebone examples added
Side-view examples added
Support Future Training ❤️
Training and developing AI models requires a significant amount of time, compute, storage, and often paid external GPU services. If you enjoy my work, any support through my Ko-fi is greatly appreciated and helps fund future training, larger datasets, and new model releases.
☕ Ko-fi: here
Recommended Companion LoRA (optional)
For stronger and rougher motion, I recommend:
Faster / Harder / Shake Harder — H3 Motion Booster (Ref2VA)
Description
~3× larger training dataset
Pronebone examples added
Side-view examples added
Improved pose variety and generalization
v1.1 focuses on improving pose coverage and consistency using a significantly expanded dataset, including new pronebone and side-view examples.
FAQ
Comments (3)
The last one was great, this one is even better so far. Early tests are promising, but it does seem to railroad some preferences. (Testing with T2V.)
Version 1.1 looks amazing.
Greattt 1.1v update!!