Training Cost
1
#16 opened 6 days ago
by
zhangyang-0123

Any further development for this?
1
#15 opened 3 months ago
by
lodestones

Sdcpp integration
2
#14 opened 4 months ago
by
stduhpf
What layers are skipped?
1
#13 opened 4 months ago
by
lavinal712

Config.json file missing
#12 opened 4 months ago
by
sakshamjoshi129

GUIDE to run on LOW VRAM here -tested on 16GB card
1
#11 opened 4 months ago
by
froilo

Is there a Lora version of this model?
4
#10 opened 4 months ago
by
Vigilence
having trouble making this work with loras
13
#9 opened 4 months ago
by
swwww55
Possible to work with 8GB VRAM and 16GB RAM?
4
#7 opened 5 months ago
by
krigeta
Do you have plans to support the stabilizability/table diffusion-3.5-large or Jimmy Carter/LibreFLUX models for this model
1
#5 opened 5 months ago
by
michaelj
Even the 8B model makes many consumer-grade graphics cards unable to run smoothly
6
#3 opened 5 months ago
by
jian2023
A theoretical formulation of how this works based on a paper by Sakana AI
1
#2 opened 5 months ago
by
NagaSaiAbhinay