
OmniBooth is a novel image generation framework that allows for precise control over the placement and appearance of multiple objects within a scene using a combination of text prompts, image references, and segmentation masks.


coremsg

omnibooth-a-unified-framework-for-controllable-image-synthesis-with-multi-modal-instance-level-instructions


OmniBooth: A Unified Framework for Controllable Image Synthesis with Multi-Modal Instance-Level Instructions


title_rewrite


Prompt Sliders enable efficient and generalizable fine-grained control, editing, and erasing of concepts in diffusion models by learning text embeddings that represent target concepts.


prompt-sliders-efficient-and-generalizable-textual-inversion-for-fine-grained-control-editing-and-erasing-of-concepts-in-diffusion-models


Prompt Sliders: Efficient and Generalizable Textual Inversion for Fine-Grained Control, Editing, and Erasing of Concepts in Diffusion Models
