Diffusion-based text-to-image generative models, e.g., Stable Diffusion, have
revolutionized the field of content generation, enabling significant
advancements in areas like image editing and video synthesis. Despite their
formidable capabilities, these models are not without their limitations. It is
still challenging to synthesize an image that aligns well with the input text,
and multiple runs with carefully crafted prompts are required to achieve
satisfactory results. To mitigate these limitations, numerous studies have
endeavored to fine-tune the pre-trained diffusion models, i.e., UNet, utilizing
various technologies. Yet, amidst these efforts, a pivotal question of
text-to-image diffusion model training has remained largely unexplored: Is it
possible and feasible to fine-tune the text encoder to improve the performance
of text-to-image diffusion models? Our findings reveal that, instead of
replacing the CLIP text encoder used in Stable Diffusion with other large
language models, we can enhance it through our proposed fine-tuning approach,
TextCraftor, leading to substantial improvements in quantitative benchmarks and
human assessments. Interestingly, our technique also empowers controllable
image generation through the interpolation of different text encoders
fine-tuned with various rewards. We also demonstrate that TextCraftor is
orthogonal to UNet finetuning, and can be combined to further improve
generative quality.

通过提出的 fine-tuning 方法 TextCraftor，我们可以增强 Stable Diffusion 使用的 CLIP 文本编码器，从而在定量基准和人类评估方面实现了显著改进，并且我们的技术还通过不同奖励的细调文本编码器的插值使得可以进行可控的图像生成，同时我们也证明了 TextCraftor 与 UNet finetuning 可以相互独立并且结合以进一步提高生成质量。