BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion

Ying Shan, Xintao Wang, Xian Liu, Qiang Xu, Yuxuan Bian, Xuan Ju

Code that ran

We lifted 3 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.

Repository	Role	Ran
tencentarc/brushnet	canonical	2 of 3

Function	Status	Where it lives
filter_float	Ran	tencentarc/brushnet/benchmarks/push_results.py pointer only (licence: NONE) · get_code("565295ed162e2027")
retrieve_timesteps	Ran	tencentarc/brushnet/src/diffusers/pipelines/brushnet/pipeline_brushnet.py pointer only (licence: NONE) · get_code("35717b791550ecb2")
zero_module	Not yet run	tencentarc/brushnet/src/diffusers/models/brushnet.py pointer only (licence: NONE) · get_code("da94debb8019ad46")

Repositories linked to this paper

tencentarc/brushnet — marked official in Papers with Code; named in the paper

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

For agents

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

get_harvested_code_for_paper("2403.06976")
get_code_for_paper("2403.06976")
have("2403.06976")

Connect an agent — have() is free.