SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2506.16504 · 2025

Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 1 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
tencent/hunyuan3d-2 canonical 1 of 10
FunctionStatusWhere it lives
get_obj_from_str Ran tencent/hunyuan3d-2/hy3dgen/shapegen/pipelines.py
pointer only (licence: NONE) · get_code("221b2d116fdf1032")
array_to_tensor Not yet run tencent/hunyuan3d-2/hy3dgen/shapegen/preprocessors.py
pointer only (licence: NOASSERTION) · get_code("9dd0c82f9c736b62")
build_image_encoder Not yet run tencent/hunyuan3d-2/hy3dgen/shapegen/models/conditioner.py
pointer only (licence: NOASSERTION) · get_code("92515a13b1c7acc3")
export_mesh Not yet run tencent/hunyuan3d-2/gradio_app.py
pointer only (licence: NOASSERTION) · get_code("c955b973f7670b5e")
gen_save_folder Not yet run tencent/hunyuan3d-2/gradio_app.py
pointer only (licence: NOASSERTION) · get_code("39256d0459ba6ee7")
get_1d_sincos_pos_embed_from_grid Not yet run tencent/hunyuan3d-2/hy3dgen/shapegen/models/conditioner.py
pointer only (licence: NOASSERTION) · get_code("7700f3428f58afbe")
load_image_from_base64 Not yet run tencent/hunyuan3d-2/api_server.py
pointer only (licence: NOASSERTION) · get_code("0dde2e782959c0bd")
pretty_print_semaphore Not yet run tencent/hunyuan3d-2/api_server.py
pointer only (licence: NONE) · get_code("37899f22fb191b37")
randomize_seed_fn Not yet run tencent/hunyuan3d-2/gradio_app.py
pointer only (licence: NOASSERTION) · get_code("c5c1412bf688b728")
retrieve_timesteps Not yet run tencent/hunyuan3d-2/hy3dgen/shapegen/pipelines.py
pointer only (licence: NOASSERTION) · get_code("607a22f436cb1076")

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 report, we present Hunyuan3D 2.5, a robust suite of 3D diffusion models aimed at generating high-fidelity and detailed textured 3D assets. Hunyuan3D 2.5 follows two-stages pipeline of its previous version Hunyuan3D 2.0, while demonstrating substantial advancements in both shape and texture generation. In terms of shape generation, we introduce a new shape foundation model -- LATTICE, which is trained with scaled high-quality datasets, model-size, and compute. Our largest model reaches 10B parameters and generates sharp and detailed 3D shape with precise image-3D following while keeping mesh surface clean and smooth, significantly closing the gap between generated and handcrafted 3D shapes. In terms of texture generation, it is upgraded with phyiscal-based rendering (PBR) via a novel multi-view architecture extended from Hunyuan3D 2.0 Paint model. Our extensive evaluation shows that Hunyuan3D 2.5 significantly outperforms previous methods in both shape and end-to-end texture generation.

For agents

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

get_harvested_code_for_paper("2506.16504")
get_code_for_paper("2506.16504")
have("2506.16504")

Connect an agent — have() is free.