LacTokGen: Latent Consistency Tokenizer for 1024-pixel Image Generation by 256 Tokens

in color and brightness discrepancies; thus, we convert it to latent consistency decoder, reducing multi-step sampling to 1-2 steps for direct pixel-level supervision. To endow LacTok with text-to-image generation capabilities, we seamlessly integrate it with an autoregressive transformer, forming LacTokGen. This transformer is trained by predicting compact token sequences conditioned on text instructions. Experiments demonstrate LacTok's superiority in high-fidelity reconstruction, with 10.8 reconstruction Fréchet Inception Distance on MSCOCO-2017 5K benchmark for 1024×1024 image reconstruction. LacTokGen achieves 0.73 score on GenEval benchmark and 0.304 HPSv2 on MSCOCO-2017 dataset.