Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

krystv
/
LiquidFlow

image-generation
flow-matching
liquid-neural-networks
mamba
state-space-models
physics-informed
lightweight
mobile-friendly
Model card Files Files and versions
xet
Community
LiquidFlow / liquidflow
Ctrl+K
Ctrl+K
  • 1 contributor
History: 11 commits
krystv's picture
krystv
v0.5 CRITICAL: Fix patch_size to scale with image size (L≤256 always), reduce d_state for speed, add config table
1c47b5f verified 8 days ago
  • __init__.py
    336 Bytes
    v0.3: update __init__.py 8 days ago
  • losses.py
    4.49 kB
    Add losses.py, sampling.py, train.py, smoke_test.py 8 days ago
  • model.py
    11.9 kB
    v0.5 CRITICAL: Fix patch_size to scale with image size (L≤256 always), reduce d_state for speed, add config table 8 days ago
  • sampling.py
    2.98 kB
    Add sampling.py — Euler and Heun ODE samplers 8 days ago
  • train.py
    16.6 kB
    Add train.py — full training script with CLI 8 days ago