Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
anime-flow-matching – AI Model by AnasKAN | AlphaNeural AI
You can deploy this model and start earning money today!
AnasKAN
/
anime-flow-matching
like
0
flow-matching
generative
anime
unconditional-image-generation
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Flow Matching — anime faces 64x64
Rectified/conditional flow matching. Predicts velocity
v = x1 - x0
along the straight path
xt = (1-t)*x0 + t*x1
, where
x0
is noise and
x1
is data.
UNet
: ch=64, mults=(1,2,2,4), attn @16 — ~16.3M params
Trained
: 30 epochs, final FM loss 0.2059
Sampling
: Euler ODE,
x += v(x,t)*dt
, ~10 steps is enough
Checkpoint contains
net
,
ema
,
opt
,
scaler
,
losses
— resumable.
Use the
ema
weights for sampling.
