Training-Free Diffusion Priors for Text-to-Image Generation via Optimization-based Visual Inversion
By: Samuele Dell'Erba, Andrew D. Bagdanov
Potential Business Impact:
Makes AI create better pictures from words.
Diffusion models have established the state-of-the-art in text-to-image generation, but their performance often relies on a diffusion prior network to translate text embeddings into the visual manifold for easier decoding. These priors are computationally expensive and require extensive training on massive datasets. In this work, we challenge the necessity of a trained prior at all by employing Optimization-based Visual Inversion (OVI), a training-free and data-free alternative, to replace the need for a prior. OVI initializes a latent visual representation from random pseudo-tokens and iteratively optimizes it to maximize the cosine similarity with input textual prompt embedding. We further propose two novel constraints, a Mahalanobis-based and a Nearest-Neighbor loss, to regularize the OVI optimization process toward the distribution of realistic images. Our experiments, conducted on Kandinsky 2.2, show that OVI can serve as an alternative to traditional priors. More importantly, our analysis reveals a critical flaw in current evaluation benchmarks like T2I-CompBench++, where simply using the text embedding as a prior achieves surprisingly high scores, despite lower perceptual quality. Our constrained OVI methods improve visual fidelity over this baseline, with the Nearest-Neighbor approach proving particularly effective, achieving quantitative scores comparable to or higher than the state-of-the-art data-efficient prior, indicating that the idea merits further investigation. The code will be publicly available upon acceptance.
Similar Papers
Instant Preference Alignment for Text-to-Image Diffusion Models
CV and Pattern Recognition
Creates images that match your exact ideas.
ProxT2I: Efficient Reward-Guided Text-to-Image Generation via Proximal Diffusion
CV and Pattern Recognition
Creates better pictures from words, faster.
Ovis-Image Technical Report
CV and Pattern Recognition
Creates clear text in pictures, even on one computer.