New 3D editors, open medical AI, AI symphony, Qwen 3.8, Wan Animate 2: AI NEWS
Unified model that generates, understands, edits via text and segments 3D objects into parts. Code is listed as coming soon.
Tencent's unified multimodal model for 3D understanding, text-to-3D generation, instruction-based editing and part generation.
Updated EU status checked Last shown
Hunyuan3D Buffalo 1.0 at a glance
- What is Hunyuan3D Buffalo 1.0?
- Hunyuan3D Buffalo 1.0 is a model from Tencent. Tencent's unified multimodal model for 3D understanding, text-to-3D generation, instruction-based editing and part generation.
- Who makes Hunyuan3D Buffalo 1.0?
- Hunyuan3D Buffalo 1.0 is made by Tencent.
- Does Hunyuan3D Buffalo 1.0 work in the EU?
- Unverified. No explicit evidence found; only a project page exists, with no public code, weights or service yet. Last verified 14 Nov 2026.
- How much does Hunyuan3D Buffalo 1.0 cost?
- Pricing unknown. No pricing or release of code/weights found; code reported as coming soon.
- Where was Hunyuan3D Buffalo 1.0 shown?
- In 1 creator video by AI Search. Most recently by AI Search on 9 Aug 2026, at 9:21 in “New 3D editors, open medical AI, AI symphony, Qwen 3.8, Wan Animate 2: AI NEWS”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
About
Hunyuan3D-Buffalo 1.0 is a research model from Tencent Hunyuan3D that handles several 3D tasks in one pipeline: 3D understanding (question answering and grounding), text-to-3D generation, instruction-guided 3D editing, and language-driven part-level generation. It connects language and 3D representations through a shared Hunyuan3D-VLM backbone, with Hunyuan3D DiT modules handling generation, editing and part generation.\n\nThe project page shows examples of text-prompted asset generation, mesh editing from natural-language instructions (source versus edited meshes), and extraction of semantic parts from a whole mesh, shown combined or exploded. A paper is cited as arXiv:2608.02711 (2026).\n\nA YouTube review states the code is listed as "coming soon". No public repository, model weights, hosted demo or pricing were found in the provided material, so access is currently limited to the project page.
Key features
- Unified model for 3D understanding, generation and editing
- Text-to-3D asset generation
- Instruction-guided 3D mesh editing via natural language
- Language-driven part-level 3D generation and decomposition
- 3D QA and grounding through a shared Hunyuan3D-VLM backbone
1 moment
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Keep exploring
Similar AI tools
Closest neighbours by meaning, not just by category.
HW
Hunyuan3D WorldClaw
Research · Tencent
Tencent Hunyuan research framework that turns one text prompt into an explorable, editable open-world 3D scene.
Unverified3D & Worlds
Release date n/a
H1
Hi3D 1.0
Model · Hi3D
Open-source image-to-3D and text-to-3D generation model from Hi3D, formerly Sparc3D, trained on ~2M curated 3D assets.
Available in EU3D & Worlds
Release date n/aOpen source
HY
Hy-Nomas
Model · Tencent
Tencent Hunyuan interactive world model generating real-time, controllable 720p video with memory for consistency.
Available in EU3D & Worlds
Release date n/aOpen source
HY
Hy4
Model · Tencent
Tencent's Hy4 multimodal model with visual understanding, computer use, 3D/Blender and knowledge-work abilities.
UnverifiedLanguage Models
Release date n/a
PI
Pixal3D
Model
Image-to-3D generator from Tsinghua and Tencent ARC Lab that builds meshes pixel-aligned to the input view.
Unverified3D & Worlds
May 2026
AR
Arbor
Model · Stability AI
Research method adding typed 3D constraint meshes (hull, avoidance, touch) as control for text-to-3D generation on TRELLIS.2.
Unverified3D & Worlds
Release date n/a