anime-flow-matching / README.md
AnasKAN's picture
Upload README.md with huggingface_hub
5e5313c verified
|
Raw
History Blame Contribute Delete
565 Bytes
metadata
tags:
  - flow-matching
  - generative
  - anime
  - unconditional-image-generation

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.