-
Add ETA to every training log line + epoch summary
-
Fix: fast VAE encoding (bs=64), auto-limit large datasets, ~5x faster caching"
-
Notebook: auto batch size, gradient checkpointing, no more OOM
-
Add gradient checkpointing + auto batch size to prevent OOM on T4
-
Add gradient checkpointing + zigzag index caching
-
Fix notebook: use pure-parquet datasets only, cartoon default
-
Fix dataset: drop broken keremberke, use pure-parquet datasets only (cartoon default, Artificio/WikiArt for styles)"
-
Fix: add trust_remote_code=True for datasets with legacy loading scripts
-
Fix notebook: use open SDXL VAE (no auth), 4ch latents, correct scaling
-
Fix VAE: switch to madebyollin/sdxl-vae-fp16-fix (open, no auth needed, 4ch latent)
-
Update README with Colab-optimized training workflow and dataset presets
-
Update notebook: latent pre-caching + small dataset presets for Colab
-
Add optimized training v2 with latent pre-caching for Colab
-
Fix: SDXL VAE (no login) + streaming dataset in notebook
-
Fix: SDXL VAE (no login), streaming dataset, step-based training
-
Fix: use SDXL VAE (4ch, no login needed)
-
Fix: streaming dataset in notebook (no full download on Colab)
-
Fix: streaming dataset (no full download), step-based training loop
-
Add Colab training notebook
-
Add training pipeline
-
Add model architecture
-
Add README with architecture docs and usage guide
-
initial commit
