Instructions to use infosave/MiniMax-H3-Turbo-cmf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- cortiq
How to use infosave/MiniMax-H3-Turbo-cmf with cortiq:
# one Rust binary, no additional dependencies cargo install cortiq-cli # or a prebuilt binary from github.com/infosave2007/cmf/releases hf download infosave/MiniMax-H3-Turbo-cmf --include "*.cmf" --local-dir . ls *.cmf # some repos ship more than one quantization
cortiq animate FILE.cmf --prompt "a corgi in a chef hat flipping a pancake" --out clip.avi
- Notebooks
- Google Colab
- Kaggle
fast mini max h3 (realtime gen) - can this be ported (open weights?)
2
#11 opened 5 days ago
by
hololabs
is this portable to cmf?
#10 opened 8 days ago
by
hololabs
unable to test chunking - raven model incorrect
#9 opened 11 days ago
by
hololabs
how do we mix in a trained likeness lora
3
#8 opened 18 days ago
by
hololabs
thread for ideas on lora/workflow/ features
24
#7 opened 18 days ago
by
hololabs
can you make LTX 2.5 · 22B INT8 ?
9
#6 opened 19 days ago
by
hololabs
can you make new cfm for next higher quality jump (ie for 32/48/64 gb)
6
#5 opened 21 days ago
by
hololabs
mac mini 24gb success story
🤝 2
9
#4 opened 21 days ago
by
hololabs
what about --audio
5
#3 opened 22 days ago
by
hololabs
how to pass in start/end frames?
11
#2 opened 22 days ago
by
hololabs
performance record
🤝 1
12
#1 opened 28 days ago
by
bingoct