← All Cracked ML projects
PL-A08NOT STARTEDADVANCEDMLPYTHONIMPACT ★★★☆☆

DDPM vs flow matching on a 12-GPU-hour budget

Same U-Net, same 12-hour budget, two generative frameworks. The FID-vs-steps curve decides.

EST.32 h
REWARD+400 XP
AFTERHo et al. + 2

ML-ARENA BENCHMARKS

PROOF: FINDING
METRICINDUSTRYMINE
FID-50k (Fréchet Inception Distance over 50k generated images; lower means more realistic and varied) vs number of function evaluations (NFE, the number of network calls one sample takes), at a fixed 12 GPU-hour training budget
GOAL · best FID ≤ 15 within 12 GPU-hours; a clear equal-budget comparison of DDPM vs flow matching at NFE 10/50/250
DDPM paper: FID 3.17 on CIFAR-10 (with a much larger budget); pytorch-fid for scoring—
no results yet
YOUR RESULTS

Your recorded results appear here.

Brief

Write a CIFAR-10 U-Net (an encoder-decoder CNN with skip connections between matching resolutions) with residual blocks, attention at 16×16, and timestep embeddings (a vector that tells the network how noisy its input is). Train it twice: once as DDPM with ε-prediction (the network predicts the noise that was added to an image) and once with conditional flow matching (the network predicts the velocity that moves a noise sample in a straight line toward a data sample). Implement DDPM, DDIM (a deterministic sampler that can skip steps) and Euler/Heun ODE samplers (first- and second-order step rules for following the learned velocity). Then compute FID-50k with pytorch-fid at NFE 10, 50 and 250.

VICTORY CONDITIONS

  1. best FID ≤ 15 within 12 GPU-hours; a clear equal-budget comparison of DDPM vs flow matching at NFE 10/50/250 (FID-50k (Fréchet Inception Distance over 50k generated images; lower means more realistic and varied) vs number of function evaluations (NFE, the number of network calls one sample takes), at a fixed 12 GPU-hour training budget).
  2. A public repository with a README that shows your result and how to reproduce it.

Terms in plain words

DDPM
Denoising diffusion: add noise to images step by step, train a network to remove it, then generate by denoising pure noise.
Flow matching
Train a network to predict the direction from a noise sample to a data sample, then generate by following that direction with an ODE solver.
DDIM
A diffusion sampler with no randomness that can take big steps, so it needs far fewer network calls.
NFE
Number of function evaluations: how many times the network runs to make one image.
FID
A distance between the feature statistics of real and generated images; lower is better.
U-Net
A CNN that downsamples then upsamples, with shortcuts that copy details from the down path to the up path.

Why it rates ★★★☆☆

A controlled equal-compute comparison is more useful than another 'my diffusion model' demo, and generative modelling is a hiring area.