SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.00571 · 2023

LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 5 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
gligen/GLIGEN extension 3 of 3
ux-decoder/segment-everything-everywhere-all-at-once pwc_unofficial 1 of 3
copy not recorded — 1 of 1
FunctionStatusWhere it lives
alpha_generator Ran this paper's copy was not recorded; identical code first harvested from YangLing0818/RealCompo
pointer only · get_code("b3e1f7172e4955ae")
alpha_generator Ran gligen/GLIGEN/demo/gligen/task_grounded_generation.py
code served (permissive licence) · get_code("a8b7b8f06a868b6f")
draw_box Ran gligen/GLIGEN/demo/gligen/task_grounded_generation.py
code served (permissive licence) · get_code("5a613694f83a9173")
project Ran gligen/GLIGEN/gligen_inference.py
code served (permissive licence) · get_code("e49923c3510ee0bc")
register_norm_module Ran ux-decoder/segment-everything-everywhere-all-at-once/utils/model.py
code served (permissive licence) · get_code("e4f6733fa1ab1999")
filter_images_with_only_crowd_annotations Not yet run ux-decoder/segment-everything-everywhere-all-at-once/datasets/build.py
code served (permissive licence) · get_code("a21a61e41d986b6a")
load_semseg Not yet run ux-decoder/segment-everything-everywhere-all-at-once/datasets/semseg_loader.py
code served (permissive licence) · get_code("eb73ad202b73f933")

Repositories linked to this paper

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

Abstract

LLaVA-Interactive is a research prototype for multimodal human-AI interaction. The system can have multi-turn dialogues with human users by taking multimodal user inputs and generating multimodal responses. Importantly, LLaVA-Interactive goes beyond language prompt, where visual prompt is enabled to align human intents in the interaction. The development of LLaVA-Interactive is extremely cost-efficient as the system combines three multimodal skills of pre-built AI models without additional model training: visual chat of LLaVA, image segmentation from SEEM, as well as image generation and editing from GLIGEN. A diverse set of application scenarios is presented to demonstrate the promises of LLaVA-Interactive and to inspire future research in multimodal interactive systems.

For agents

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

get_harvested_code_for_paper("2311.00571")
get_code_for_paper("2311.00571")
have("2311.00571")

Connect an agent — have() is free.