Sigrid has come to Minimax H3. For consistent voice generation and body/face when rendering image-to-video, this model will give you the full Sigrid package. Full natural motion is baked in so you don't need other LoRAs unless you want a specific kind of action, scene, or clothing that I didn't include in the dataset.
Important: This model is 100% fictitious and is not based on images of any real person. She originated with images generated from still image checkpoints and has evolved from there using only AI rendering. No images (neither actual nor AI-generated) of any real person was ever involved in the making of this model.
Strength: 0.75 for text-to-video
keyword: sigrid (example: "...a sigrid woman is...")
favorite sampler/scheduler: er_sde / sgm_uniform
Sigrid has companion models for other video engines as well as still images, so you have lots of options for putting together a Sigrid scene. Enjoy!
Description
FAQ
Comments (9)
how do you train models? ai toolkit? can it be done via yaml file?
Until recently I was using musubi tuner on the command line and it was honestly very complicated but it was working for me. Right now, ai toolkit seems to be the best (nearly the only) trainer for h3 and that tool recently added block swapping to help manage memory on regular person computers like mine. So my h3 models have been made on ai toolkit and I like it so far.
busty sophie next? :)
Actually I have Candi queued up to publish very shortly, I worked on that model and Sigrid's side by side.
I appreciate knowing Sophie has fans, though, and she might be next in line. I also want to get Shannon on H3.
whats sigrid?
Who, not what. She is. Sigrid is a common name throughout Scandinavia
Bimbo adventures in Minimax!
Another awesome job!
Would you mind sharing your AI Toolkit method? Your models always have such great skin texture, micro details etc. How do you capture that in the training?
I can share a config file from one of the character training runs later when I have a bit more time, but short version is I'm actually doing a very low memory training run on my home computer which has 16gb vram.
I train with a bunch of still photos at 640x960 to give good character identity with different angles and plenty of face close-ups. Then I add maybe 20 videos at very small resolution (like 240x360) at full 24fps with sound in order to get the voice added to the model and the video will have some face and mouth movement that helps too. I try to include some other body motions to help give some natural movement too but it's all very low-res. Seems to work ok though.
I train the model at 16/16 instead of 32 or higher, which gives a 150mb file, give or take. All the other settings are pretty much defaults, but I use the 4bit nvidia versions of the main model and voice model to save memory and I still have to do block swapping to get it to run without crashing.
If that's not enough, let me know and I can paste in a config file later.