text-guided-image-editing
22 papers with code • 0 benchmarks • 0 datasets
Editing images using text prompts.
Benchmarks
These leaderboards are used to track progress in text-guided-image-editing
Most implemented papers
InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions
In this work, we propose a framework termed InstructEdit that can do fine-grained editing based on user instructions.
MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing
osu-nlp-group/magicbrush
•
•
NeurIPS 2023
To address this issue, we introduce MagicBrush (https://osu-nlp-group. github. io/MagicBrush/), the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing.
Masked-Attention Diffusion Guidance for Spatially Controlling Text-to-Image Generation
endo-yuki-t/mag
•
•
To address this issue, we propose masked-attention guidance, which can generate images more faithful to semantic masks via indirect control of attention to each word and pixel by manipulating noise images fed to diffusion models.
Forgedit: Text Guided Image Editing via Learning and Forgetting
witcherofresearch/forgedit
•
•
Text-guided image editing on real or synthetic images, given only the original image itself and the target text prompt as inputs, is a very general and challenging task.
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
fast-codi/CoDi
•
•
Our conditional-task learning and distillation approach outperforms previous distillation methods, achieving a new state-of-the-art in producing high-quality images with very few steps (e. g., 1-4) across multiple tasks, including super-resolution, text-guided image editing, and depth-to-image generation.
DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing
Based on DeltaSpace, we propose a novel framework called DeltaEdit, which maps the CLIP visual feature differences to the latent space directions of a generative model during the training phase, and predicts the latent space directions from the CLIP textual feature differences during the inference phase.
Lasagna: Layered Score Distillation for Disentangled Object Relighting
dbash/lasagna
•
•
Although generative editing methods now enable some forms of image editing, relighting is still beyond today's capabilities; existing methods struggle to keep other aspects of the image -- colors, shapes, and textures -- consistent after the edit.
Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models
yandex-research/adaptive-diffusion
•
•
While several powerful distillation methods were recently proposed, the overall quality of student samples is typically lower compared to the teacher ones, which hinders their practical usage.
SpecRef: A Fast Training-free Baseline of Specific Reference-Condition Real Image Editing
To increase user freedom, we propose a new task called Specific Reference Condition Real Image Editing, which allows user to provide a reference image to further control the outcome, such as replacing an object with a particular one.
Diffusion Model-Based Image Editing: A Survey
siatmmlab/awesome-diffusion-model-based-image-editing-methods
•
•
In this survey, we provide an exhaustive overview of existing methods using diffusion models for image editing, covering both theoretical and practical aspects in the field.
