We generally perceive that training text-to-image diffusion models requires heavy compute: it is true if we aim at a comprehensive frontier model. This understanding prevents people from training their own models when getting started in the field. We develop MiniDog, a framework that enables pretraining diffusion transformers in 55 minutes and fine-tuning in another 15 minutes on four 3090 GPUs. For data, we use 26k dog images from ImageNet and caption them for pretraining and use 2k images generated by FLUX.1-schnell for fine-tuning. We precompute the image and text features and cache them for efficiency. For architecture, we use E2E-INVAE for its semantic latent space, a small transformer with 22M parameters, a small Qwen model for text encoding, and in-context conditioning. For training, we use iREPA and an EUPE perception encoder for acceleration. For evaluation, our repository supports FID, HPSv2 score, PickScore, and various VAE reconstruction metrics.
Figures & tables
Figure 1: Samples from the SFT model. Prompts of the highlighted samples: “Golden Retriever with a dark golden, freshly brushed…” “Corgi with a clean fawn-and-white coat stands alert…” “Samoyed with a fluffy biscuit double coat sleeps curled…”
Figure 2: T2I pretraining recipe. Frozen Qwen3 [ 14 ] , E2E-INVAE [ 13 ] and EUPE ViT-B/16 [ 15 ] produce the text embeddings, the latents (noised with ϵ ) and the alignment targets. LightningDiT [ 7 ] is pretrained with the flow-matching loss [ 2 ] and the iREPA [ 11 ] loss on Block 4.
Figure 3Figure 4
HPSv2
PickScore
Pretrained
0.1625
18.42
SFT
0.2427
19.61
Table 4: Human-preference scores of the pretrained and SFT ckpts.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Pretraining
SFT
Architecture
Backbone
LightningDiT
Input dim.
16×16×32
Patch size
1
Num. layers
12
Hidden dim.
384
Appendix
Table 5: Hyperparameters of the final recipe ( configs/pretrain_e2e-invae_128tok_mse_irepa_eupe.yaml and configs/sft_e2e-invae_128tok_mse_norepa.yaml ).