IdeaCredIdeaCred

pablo-reyes8/conditioning-stable-diffusion

73

Latent diffusion model for attribute-conditioned face generation, with reproducible data ingestion, YAML-configured training and inference, offline evaluation through FID, KID, Inception Score, and pre-trained face detection.

What's novel

Latent diffusion model for attribute-conditioned face generation, with reproducible data ingestion, YAML-configured training and inference, offline evaluation through FID, KID, Inception Score, and pre-trained face detection.

Code Analysis

17 files read · 5 rounds

A from-scratch latent diffusion training and inference pipeline that generates faces conditioned on binary attributes (e.g., Smiling, Young, Male) using a custom UNet with cross-attention, Classifier-Free Guidance, and a pretrained Stable Diffusion VAE for latent encoding/decoding.

Strengths

Genuinely implements the core diffusion components (UNet, DDPM/DDIM, attention, Min-SNR loss, CFG) from scratch with careful attention to training stability (zero-init, EMA health checks, OOM recovery, gradient accumulation), and provides a complete reproducible workflow from data ingestion through evaluation with FID/KID/IS metrics.

Weaknesses

The label conditioning is limited to 11 binary attributes via a simple embedding interpolation rather than text-based conditioning, the test suite is thin (mostly smoke tests with tiny dummy models rather than verifying numerical correctness of diffusion math), and some Colab-specific code (Drive mounting) is mixed into the core training orchestrator.

Score Breakdown

Innovation
5 (25%)
Craft
62 (35%)
Traction
6 (15%)
Scope
82 (25%)

Signal breakdown

Innovation

Not Fork+1
Code Novelty+1
Concept Novelty+1

Craft

Ci+0
Tests+8
Polish+0
Releases+0
Has License+0
Code Quality+22
Readme Quality+15
Recent Activity+7
Structure Quality+5
Commit Consistency+0
Has Dependency Mgmt+5

Traction

Forks+0
Stars+6
Hn Points+0
Watchers+0
Early Traction+0
Devto Reactions+0
Community Contribs+0

Scope

Commits+5
Languages+5
Subsystems+13
Bloat Penalty+0
Completeness+6
Contributors+5
Authored Files+15
Readme Code Match+3
Architecture Depth+7
Implementation Depth+8

Evidence

Commits

11

Contributors

1

Files

134

Active weeks

2

TestsCI/CDREADMELicenseContributing

Repository

Language

Python

Stars

1

Forks

0

License