SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.09739 · 2024

TraDiffusion: Trajectory-Based Training-Free Image Generation

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
och-mac/tradiffusion canonical 2 of 5
FunctionStatusWhere it lives
compute_ca_loss_masks Ran och-mac/tradiffusion/utils.py
pointer only (licence: NONE) · get_code("529c68d68a7fba80")
find_tensor_positions Ran och-mac/tradiffusion/utils.py
pointer only (licence: NONE) · get_code("a57d2a7e92fbddd5")
concat_images Not yet run och-mac/tradiffusion/utils.py
pointer only (licence: NONE) · get_code("6385eb1bcdf2344e")
get_down_block Not yet run och-mac/tradiffusion/my_model/unet_2d_blocks.py
pointer only (licence: NONE) · get_code("249a089f948c8cb4")
get_up_block Not yet run och-mac/tradiffusion/my_model/unet_2d_blocks.py
pointer only (licence: NONE) · get_code("c3f3e72710fb5556")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we propose a training-free, trajectory-based controllable T2I approach, termed TraDiffusion. This novel method allows users to effortlessly guide image generation via mouse trajectories. To achieve precise control, we design a distance awareness energy function to effectively guide latent variables, ensuring that the focus of generation is within the areas defined by the trajectory. The energy function encompasses a control function to draw the generation closer to the specified trajectory and a movement function to diminish activity in areas distant from the trajectory. Through extensive experiments and qualitative assessments on the COCO dataset, the results reveal that TraDiffusion facilitates simpler, more natural image control. Moreover, it showcases the ability to manipulate salient regions, attributes, and relationships within the generated images, alongside visual input based on arbitrary or enhanced trajectories.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.09739")
get_code_for_paper("2408.09739")
have("2408.09739")

Connect an agent — have() is free.