- Home›
- Categories›
- Image Editing
Image Editing
AI Tools
DiffUHaul
DiffUHaul is a groundbreaking approach for seamless object relocation in images, leveraging the spatial understanding capabilities of localized text-to-image diffusion models.
FLUX Canny
Part of FLUX Tools, FLUX Canny allows users to guide transformations using edge detection.
FLUX Depth
Part of FLUX Tools, FLUX Depth introduces depth-aware image editing, leveraging depth maps to maintain structure and proportions during transformations.
FLUX Redux
Part of FLUX Tools, FLUX Redux offers an innovative way to reimagine images by creating stylistic variations or entirely new looks.
FLUX Fill
Part of FLUX Tools, FLUX Fill enables state-of-the-art inpainting and outpainting, allowing users to seamlessly edit or expand real and generated images.
From Text to Pose to Image
"From Text to Pose to Image" introduces a groundbreaking method for generating high-quality images from text prompts. This multi-step approach first creates human poses based on the text input, then uses these poses to guide the final image generation.
Stable Flow
Stable Flow is a groundbreaking, training-free approach to image editing built on the Diffusion Transformer (DiT) architecture.
OOTDiffusion
OOTDiffusion AI is a cutting-edge, open-source tool that empowers fashion designers and creatives to transform models' outfits into custom, high-fashion designs
InstantIR
InstantIR is a breakthrough AI tool for Blind Image Restoration (BIR) that can repair severely degraded images and enhance them with stunning detail. Developed
Constrained Diffusion Implicit Models (CDIM)
Constrained Diffusion Implicit Models (CDIM) leverage the power of diffusion models to efficiently solve a variety of noisy inverse problems such as inpainting, sparse recovery, and colorization.
ACE Chat
ACE is an AI Chat for Image Editing and Generation, offering an all-in-one approach that leverages diffusion transformers for seamless image manipulation.
SGEdit
SGEdit is an innovative image editing tool that combines large language models (LLM) with text-to-image generative models to enable highly precise and flexible image editing based on scene graphs.
© 2024 – Opendemo