A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models

Wangxuan Institute of Computer Technology
Peking University

UDiffText can synthesize the text you want in arbitrary images


Text-to-Image (T2I) generation methods based on diffusion model have garnered significant attention in the last few years. Although these image synthesis methods produce visually appealing results, they frequently exhibit spelling errors when rendering text within the generated images. Such errors manifest as missing, incorrect or extraneous characters, thereby severely constraining the performance of text image generation based on diffusion models. To address the aforementioned issue, this paper proposes a novel approach for text image generation, utilizing a pre-trained diffusion model (i.e., Stable Diffusion).

Our approach involves the design and training of a light-weight character-level text encoder, which replaces the original CLIP encoder and provides more robust text embeddings as conditional guidance. Then, we fine-tune the diffusion model using a large-scale dataset, incorporating local attention control under the supervision of character-level segmentation maps. Finally, by employing an inference stage refinement process, we achieve a notably high sequence accuracy when synthesizing text in arbitrarily given images. Both qualitative and quantitative results demonstrate the superiority of our method to the state of the art. Furthermore, we showcase several potential applications of the proposed UDiffText, including text-centric image synthesis, scene text editing, etc.

Visualization of the denoising diffusion process.


We aim to design a unified framework for high-quality text synthesis in both synthetic and real-world images. The proposed method, UDiffText, is built based on the inpainting variant of Stable Diffusion (v2.0). Specifically, we first design and train a light-weight character-level (CL) text encoder as a substitute for the original CLIP text encoder. Then, we train the model using the denoising score matching (DSM) loss in conjunction with the local attention loss and scene text recognition loss.


An overview of the training process of our proposed UDiffText. We build our model based on the inpainting version of Stable Diffusion (v2.0). A character-level (CL) text encoder is utilized to obtain robust embeddings from the text to be rendered. We train the model using denoising score matching (DSM) together with the local attention loss calculated based on character-level segmentation maps and the auxiliary scene text recognition loss. Note that only the parameters of cross-attention (CA) blocks are updated during training.

More Results

cars peace

cars peace

Scene text editing with UDiffText.


        title={UDiffText: A Unified Framework for High-quality Text Synthesis in Arbitrary Images via Character-aware Diffusion Models}, 
        author={Yiming Zhao and Zhouhui Lian},