One LoRA, two camera tricks for MiniMax-H3 Ref2VA. Pick the mode with the prompt.
Card spin Trigger: ORB360_CARDSPIN
Your photo turns in space like a thin photo card: profile on the edge, the back of the head on the back, then it lands back on your photo. Uses one photo.
360° orbit Trigger: ORB360_CW
A smooth clockwise camera orbit around your frozen subject, ending on the starting view. The photo's surroundings are kept. It is fairly easy to prompt for a grey studio background as well for subject isolation.
Works from one photo, or better from three views of the same subject (for example three renders or a turnaround sheet): the front, the view 120° clockwise around it, and the view 240° around. With real side and back views the model does not have to invent them.
How to use
- Load LoRA at strength 1.0 on the MiniMax-H3 Ref2VA model.
- Paste the matching prompt as the text (all on Hugging Face, link below):
- card spin, one photo: cardspin_caption.txt
- orbit, one photo: orbit_realscene_caption.txt
- orbit, three views: orbit_3ref_caption.txt
- In ComfyUI, use the MiniMax H3 Reference to Video node. Connect the photos in order: ref_image_1 is the start view (Picture 1), ref_image_2 the 120° view (Picture 2), ref_image_3 the 240° view (Picture 3). Keep ref_image_size on "match".
- 124 frames at 24 fps; the prompts' timings assume that length.
- The prompts keep the output silent. Roll a few seeds.
Prompts, example files and the full training notes:
https://huggingface.co/MATLOWAI/MiniMax-H3-ORB360-CardSpin
The card effect was learned from one clip made from a public-domain 1867 photograph; this is not a likeness model.
Licence: MiniMax H3 Community License Agreement. Powered by MiniMax H3.
Description
FAQ
Comments (5)
I think this will be my new favourite one for a while.
Great work! Congratulations.
I have not tested, but is it possible with this Lora or if we could get one that would make a 360 orbit but not around left-right, but like going up and then coming back around from the bottom?
Probably not. I added some more height controls with + and - indicators in v2 that im generating example cats for right now and you might have some luck but it might be a bit roll of the dice. probably wont take much more training now that it knows generally whats going on though I can add that to an overnight run and see if it retains all the other understanding well enough.
From one Az to another:
Blender animation as reference;
ref2vid;
be sure to lower the resolution on the video reference and color the sides of the model in blender. A cube is sufficient for most work.