Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs

arXiv:2610.18870v1 Announce Type: new Abstract: 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.

Related

• Shifting the Breaking Point of Flow Matching for Multi-Instance Editing
• FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation
• DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
• VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation

Source: arXiv cs.CV | 2026-10-14