Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
This addresses the need for culturally distinctive dish images in the digitized food industry and e-commerce, but it is incremental as it adapts existing methods to a specific domain.
The authors tackled the problem of generating photorealistic and faithful images of Chinese dishes, which existing text-to-image models struggle with, by proposing Omni-Dish, a specialized model that achieves superior results through a comprehensive dataset and training scheme.
Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and e-commerce. In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes. To address this limitation, we propose Omni-Dish, the first text-to-image generation model specifically tailored for Chinese dishes. We develop a comprehensive dish curation pipeline, building the largest dish dataset to date. Additionally, we introduce a recaption strategy and employ a coarse-to-fine training scheme to help the model better learn fine-grained culinary nuances. During inference, we enhance the user's textual input using a pre-constructed high-quality caption library and a large language model, enabling more photorealistic and faithful image generation. Furthermore, to extend our model's capability for dish editing tasks, we propose Concept-Enhanced P2P. Based on this approach, we build a dish editing dataset and train a specialized editing model. Extensive experiments demonstrate the superiority of our methods.