Results 11 to 20 of about 4,250,670 (346)
InstructPix2Pix: Learning to Follow Image Editing Instructions [PDF]
Computer Vision and Pattern Recognition, 2022 We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image.
Tim Brooks +2 more
semanticscholar +1 more source
Prompt-to-Prompt Image Editing with Cross Attention Control [PDF]
International Conference on Learning Representations, 2022 Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text prompts.
Amir Hertz +5 more
semanticscholar +1 more source
Imagic: Text-Based Real Image Editing with Diffusion Models [PDF]
Computer Vision and Pattern Recognition, 2022 Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently limited to one of the following: specific editing types (e.g., object overlay, style transfer), synthetically generated images, or requiring ...
Bahjat Kawar +7 more
semanticscholar +1 more source
MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing [PDF]
Neural Information Processing Systems, 2023 Text-guided image editing is widely needed in daily life, ranging from personal use to professional applications such as Photoshop. However, existing methods are either zero-shot or trained on an automatically synthesized dataset, which contains a high ...
Kai Zhang +4 more
semanticscholar +1 more source
Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions [PDF]
IEEE International Conference on Computer Vision, 2023 We propose a method for editing NeRF scenes with text-instructions. Given a NeRF of a scene and the collection of images used to reconstruct it, our method uses an image-conditioned diffusion model (InstructPix2Pix) to iteratively edit the input images ...
Ayaan Haque +4 more
semanticscholar +1 more source
TokenFlow: Consistent Diffusion Features for Consistent Video Editing [PDF]
International Conference on Learning Representations, 2023 The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content.
Michal Geyer +3 more
semanticscholar +1 more source
Unified Concept Editing in Diffusion Models [PDF]
IEEE Workshop/Winter Conference on Applications of Computer Vision, 2023 Text-to-image models suffer from various safety issues that may limit their suitability for deployment. Previous methods have separately addressed individual issues of bias, copyright, and offensive content in text-to-image models.
Rohit Gandikota +4 more
semanticscholar +1 more source
DragDiffusion: Harnessing Diffusion Models for Interactive Point-Based Image Editing [PDF]
Computer Vision and Pattern Recognition, 2023 Accurate and controllable image editing is a challenging task that has attracted significant attention recently. Notably, DRAGGAN developed by Pan et al.
Yujun Shi +5 more
semanticscholar +1 more source
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 The information stored in large language models (LLMs) falls out of date quickly, and retraining from scratch is often not an option. This has recently given rise to a range of techniques for injecting new facts through updating model weights.
Zexuan Zhong +4 more
semanticscholar +1 more source
Editing Models with Task Arithmetic [PDF]
International Conference on Learning Representations, 2022 Changing how pre-trained models behave -- e.g., improving their performance on a downstream task or mitigating biases learned during pre-training -- is a common practice when developing machine learning systems.
Gabriel Ilharco +6 more
semanticscholar +1 more source