Rodin Gen-2

Rodin Gen-2 is a generative artificial intelligence model for producing three dimensional assets from text prompts or reference images, developed by the Shanghai based company Deemos and delivered through the company's Hyper3D creation platform at hyper3d.ai. The model was first opened for trials on 5 August 2025 and received its formal commercial launch on 1 October 2025 as a native 3D foundation model with roughly 10 billion parameters, following a debut at SIGGRAPH 2025 where Deemos won the conference Best Paper Award for related research ^[1][3][4]. It introduces a recursive part based generation method built on the team's BANG research, which lets the system produce complex objects as a set of clean, separable components rather than as a single fused mesh ^[1].

Rodin Gen-2 succeeds Rodin Gen-1, which Deemos opened for public trials on 30 May 2024 with a 1.5 billion parameter model, and the intermediate Rodin 1.5 release of 29 April 2025 ^[9][10]. A revised checkpoint dated 20 November 2025 added native 3D texture generation aimed at removing visible UV seams ^[8]. Deemos then shipped a further upgrade, Rodin Gen-2.5, on 26 May 2026, adding sculpt level geometric detail and adaptive speed controls that range from four second drafts to raw meshes exceeding 10 million polygons ^[21]. The product is positioned for game development, visual effects, e commerce visualisation, and consumer 3D printing, and competes with Tencent Hunyuan 3D, Tripo P1 from Tripo AI, and Meshy 6 in the wider 3D generation market.

Background

Deemos was founded in 2020 by Wu Di and Zhang Qixuan, two students from ShanghaiTech University, and is headquartered in the China Shanghai Pilot Free Trade Zone ^[19]. The company first attracted attention with WAND, a GAN based sketch to image consumer app released in 2020 that reached the top of the Apple App Store Graphics and Design category in both China and Japan and accumulated roughly 1.6 million users in two weeks ^[8]. Between 2021 and 2023 Deemos pivoted to high fidelity 3D scanning, building a light stage style capture system called the Plenoptic Stage that recorded around 2,000 actors with sub micron geometric and material precision ^[8]. Observing that paying customers preferred AI generated assets over scanned ones, the team moved into generative 3D from 2023 onwards.

The company runs the consumer and enterprise platform Hyper3D, which currently hosts three products: the ChatAvatar character generator, the Rodin general 3D asset generator, and the OmniCraft 3D tool suite ^[8][14]. Deemos has been backed by Sequoia China Seed Fund, MiraclePlus, BlueRun Ventures, and DragonBall Capital across its early rounds, and the company secured a Series A round co led by Meituan DragonBall and ByteDance in 2025 ^[18].

What were Rodin Gen-1 and Rodin 1.5?

The Rodin product line started with the public trial of Rodin Gen-1 on 30 May 2024 ^[10]. That first version was built on what Deemos called a 3D native large model with 1.5 billion parameters, and produced quad faced meshes with physically based rendering materials in around 40 seconds per asset. Rodin Gen-1 was the first commercial generative 3D system to advertise direct usability for 3D printing, and Deemos reported reaching an annual recurring revenue of roughly one million US dollars within 45 days of launch ^[9].

Rodin 1.5 followed on 29 April 2025. It scaled the underlying model to roughly 4 billion parameters and tightened the topology of the output meshes ^[9]. The 1.5 release also expanded the Hyper3D web platform with team workspaces, asset libraries, and an early image to 3D mode aimed at concept artists. Rodin 1.5 was the model that prepared the company's third SIGGRAPH appearance and provided the production baseline that Gen-2 was benchmarked against.

When was Rodin Gen-2 released and what can it do?

Deemos demonstrated Rodin Gen-2 live at SIGGRAPH 2025 in Vancouver in August 2025 and made early access available to existing Hyper3D subscribers from 5 August 2025 ^[3]. The full commercial launch followed on 1 October 2025, with a press release positioning Rodin Gen-2 as a 10 billion parameter native 3D foundation model ^[1][4]. The 20 November 2025 update, sometimes referred to inside the platform as build 1120, introduced a native 3D texture pipeline that the company says eliminates the seam artefacts associated with the older multi view to UV baking approach ^[8].

The table below summarises the capabilities disclosed in Deemos materials and independent reviews of the model.

Scroll sideways for more →

Deemos does not publish a public benchmark suite for Gen-2, so the headline four times improvement in mesh quality versus Rodin 1.5 comes from internal evaluation ^[1]. Independent reviewers at gaga.art and PixelDojo report that the topology is noticeably cleaner than competing systems on hard surface objects, while highly detailed organic forms can still need manual refinement and exact proportions in the output should be treated as approximate rather than measured ^[5][7].

What is Rodin Gen-2.5?

Rodin Gen-2.5 is the current flagship version of the model, released on 26 May 2026, which Deemos describes as bringing sculpt level detail and production control to AI 3D generation ^[21]. It replaces the single fixed generation pass of Gen-2 with adaptive speed and quality modes: a user can request a draft in about four seconds, or step up through 9, 20, 40, and 80 second tiers for progressively higher fidelity output ^[21]. At the top end the model can emit raw meshes exceeding 10 million polygons, and it exposes three distinct topology options: raw triangle meshes for maximum detail, quad meshes for structured editing and refinement, and Smart Low-Poly outputs optimised for real time use ^[21].

The 2.5 release also extends the native 3D texturing introduced in late 2025, adding improved 360 degree texture coverage and more consistent physically based rendering materials across the full surface of a model, which addresses the incomplete texturing that single image to 3D workflows tended to leave on unseen faces ^[21]. Qixuan Zhang, CTO of Deemos, said that "Rodin Gen-2.5 pushes AI-generated 3D assets into a new level of geometric detail. From million-polygon generation in seconds to raw outputs exceeding 10 million polygons, Gen-2.5 gives creators adaptive control over speed, fidelity, texture consistency, and topology." ^[21] Deemos has not disclosed a separate parameter count for Gen-2.5, which builds on the same 10 billion parameter foundation trained for Gen-2.

How does Rodin Gen-2 work?

The Rodin Gen-2 backbone scales to roughly 10 billion parameters, several times the size of the 1.5 billion parameter Rodin Gen-1 model and more than double the 4 billion parameter Rodin 1.5 ^[1][4]. The technical lineage runs through three peer reviewed papers from the Deemos and ShanghaiTech team. The first is CLAY, a controllable large scale generative model for 3D assets that received the Best Paper Honorable Mention at SIGGRAPH 2024 and introduced the team's 3D native diffusion pipeline based on a 3DShape2VecSet style representation ^[8]. The second is CAST, a component aligned 3D scene reconstruction method from a single RGB image, which won the Best Paper Award at SIGGRAPH 2025 on 14 August 2025 after three prior nominations ^[3]. The third is BANG, the technique that gives Rodin Gen-2 its part level behaviour.

BANG and recursive part based generation

BANG, whose full paper title is "BANG: Dividing 3D Assets via Generative Exploded Dynamics," was authored by Longwen Zhang, Qixuan Zhang, Haoran Jiang, Yinuo Bai, Wei Yang, Lan Xu, and Jingyi Yu, with affiliations at ShanghaiTech University, Deemos Technology, and Huazhong University of Science and Technology ^[12]. The paper was published in ACM Transactions on Graphics (volume 44, issue 4, 2025) and selected as one of the Top 10 Technical Papers Fast Forward presentations at SIGGRAPH 2025 ^[12][13]. SIGGRAPH attendees later voted it into the conference Top 10 Presentations list overall ^[11].

BANG treats 3D asset creation as a process of progressive decomposition. Given a target object, the model produces a tree of parts: legs, seat, backrest, and arms for a chair, for example, with each component generated as a separate mesh and the relative spatial arrangement preserved. The Generative Exploded Dynamics view in the Hyper3D interface visualises this decomposition by animating the parts outward from the assembled position, letting a user inspect, edit, or swap individual components. Inside Rodin Gen-2 the same machinery underpins the recursive part based generation feature, where the model can subdivide a complex object into coherent components and continue refining each component independently rather than producing a single fused mesh ^[1].

3D ControlNet conditioning

Rodin Gen-2 accepts three spatial conditioning inputs in addition to text or image prompts. Bounding box control fixes the gross dimensions of an asset, voxel control supplies a coarse occupancy grid that the diffusion process must respect, and point cloud control provides a sparse surface guide ^[1]. Deemos positions this as a 3D analogue of ControlNet in the 2D image generation world. The platform exposes the three inputs through the same web interface used for plain text and image generation.

Mesh and texture pipeline

The model emits quad biased meshes with baked normal maps, which lets a high polygon shape display its surface detail on a low polygon proxy suitable for real time rendering ^[1]. Texture output includes albedo, metallic, and roughness maps, with the 20 November 2025 update replacing the older multi view to UV baking step with a native 3D texture generator that paints the surface directly in three dimensional space ^[8]. Deemos says this removes the dead angle seams that appear when a UV chart is laid out poorly, although this has not yet been independently benchmarked.

What is the Hyper3D platform?

Hyper3D is the consumer and enterprise web application that hosts Rodin Gen-2, ChatAvatar, and OmniCraft. It is accessed at hyper3d.ai and is operated directly by Deemos ^[14]. The Rodin generator inside Hyper3D supports text prompts, single reference images, and the three ControlNet inputs, and exports to FBX, GLB, and OBJ files with optional PBR texture sets ^[14]. The platform also hosts a community gallery of generated assets and a credit ledger that tracks usage against subscription quotas.

The Rodin Gen-2 Edit feature, introduced after the October 2025 launch and discussed in an Animation World Network interview with CTO Zhang Qixuan, lets users upload an existing 3D model and modify it using natural language prompts ^[6]. Zhang framed 2026 around this shift, saying that "In 2026, our main focus is on the 3D editing, which means you can upload your own model to our website and edit it with AI tools." ^[8] The goal, according to Zhang, is to move from one shot generation toward iterative editing workflows that look closer to how human artists actually work. Hyper3D also supports an API path so that the same generation and editing primitives can be invoked from third party tools, and Rodin Gen-2 has been integrated into hosted inference platforms including WaveSpeedAI ^[16][17].

The platform has also seen enterprise adoption. In April 2026, NVIDIA published a case study on the home improvement retailer Lowe's, the second largest such retailer in the world, in which Hyper3D Rodin powered an AI driven 2D to 3D conversion pipeline that supported a catalogue of more than 30,000 product assets, generating each model within minutes at a cost of under one US dollar per model ^[22].

How much does Rodin Gen-2 cost?

Deemos prices Rodin Gen-2 access on a tiered subscription model billed in US dollars per month, with all tiers granting full commercial usage of generated assets ^[23]. The free tier provides a limited trial, while paid tiers add monthly credit allocations and access to advanced features. The table below summarises the disclosed plans as documented in the official Hyper3D pricing page and independent reviews of the platform.

Scroll sideways for more →

New Hyper3D accounts received a 14 day Creator Plan trial at launch under the promotional code bnaRodinGen2, distributed through the befores and afters coverage of the Gen-2 announcement ^[1]. The earlier Rodin Gen-1 product had used a generation is free, download is paid pricing model, where users only spent credits when they accepted a result and downloaded the file ^[9]. Some elements of that model persist in the free tier of the Gen-2 era platform, where the current pricing page advertises the ability to generate for free before confirmation ^[23].

How does Rodin Gen-2 compare to Hunyuan 3D, Tripo, and Meshy?

The table below positions Rodin Gen-2 against three commonly cited rivals in the generative 3D space as of mid 2026. Figures come from each vendor's public documentation and from independent reviews where cited; capabilities not confirmed by primary sources are left blank.

Scroll sideways for more →

Reviewers at the 3D AI Studio benchmark roundup and the Vset3D channel converge on a similar pattern. Hunyuan 3D is favoured for hard surface modelling and for the price of admission since the weights are free to download within the licensed territory. Tripo is praised for organic creatures and stylised content and for fast iteration. Meshy is rated highly for product polish, documentation, and security certifications including SOC 2 and ISO 27001. Rodin Gen-2 is positioned as the realism and structural quality leader for higher budget productions, and it is the only one of the four to advertise a true part level decomposition mode for downstream editing. Independent reviewers also note that Rodin's pricing is at the premium end of the market, especially for studios that need high credit budgets.

Reception

Industry coverage of Rodin Gen-2 has been broadly positive. befores and afters described the launch as a groundbreaking step for intuitive 3D creation, the Animation World Network ran two pieces on the model including a follow up interview with the Hyper3D CTO, and PixelDojo positioned the system as the new high water mark for professional generative 3D ^[1][2][5][6]. Coverage repeatedly highlights three points: the 10 billion parameter scale of the model, the four times improvement in geometric mesh quality claimed against Rodin 1.5, and the part level generation behaviour inherited from the BANG paper.

Academic reception has tracked the SIGGRAPH 2025 publication cycle. The CAST paper won the conference's Best Paper Award on 14 August 2025, BANG was named in the Top 10 Technical Papers Fast Forward list and later voted into the SIGGRAPH attendee Top 10 Presentations, and the team's earlier CLAY paper continues to be cited in subsequent 3D generative AI work ^[3][11]. Qixuan Zhang, CTO of Deemos, called the recognition "a tremendous honor and a powerful validation of our team's persistent, research-driven approach to solving fundamental challenges in 3D AI." ^[3] Deemos used the conference appearance both for academic outreach and to demonstrate Rodin Gen-2 live at its booth, a combination that the company has used at SIGGRAPH every year since 2023.

The most common criticisms in independent reviews target three areas. The first is pricing, since the credit based subscription model can run up costs quickly for studios that produce hundreds of assets per month. The second is detail handling on highly organic forms, where reviewers note that hair, fabric folds, and very fine surface detail can still require manual cleanup ^[7]. The third is the closed weights model, which means that users cannot run Rodin Gen-2 locally and must rely on the Hyper3D cloud or partner inference platforms. The competitive comparison with Hunyuan 3D, where Tencent ships open weights under a community licence, recurs in many of these reviews.

See also

• Deemos
• Hyper3D
• Hunyuan 3D
• Tripo P1
• Meshy 6
• 3D generation
• Tencent

References

1. befores and afters. "Deemos Launches Rodin Gen-2, A Groundbreaking Generative AI for Intuitive 3D Creation." 2 October 2025. https://beforesandafters.com/2025/10/02/deemos-launches-rodin-gen-2-a-groundbreaking-generative-ai-for-intuitive-3d-creation/ ↩
2. Animation World Network. "Deemos Launches Groundbreaking Rodin Gen-2 GenAI for Intuitive 3D Creation." October 2025. https://www.awn.com/news/deemos-launches-groundbreaking-rodin-gen-2-genai-intuitive-3d-creation ↩
3. Press Advantage. "Deemos Wins SIGGRAPH 2025 Best Paper Award, Debuts Rodin Gen-2 Text-to-3D Foundation Model." 15 August 2025. https://pressadvantage.com/story/81414-deemos-wins-siggraph-2025-best-paper-award-debuts-rodin-gen-2-text-to-3d-foundation-model ↩
4. Press Advantage via FinancialContent. "Deemos Tech Launches Hyper3D Rodin Gen-2: Next-Generation 3D Model Generator." 1 October 2025. https://markets.financialcontent.com/stocks/article/pressadvantage-2025-10-1-deemos-tech-launches-hyper3d-rodin-gen-2-next-generation-3d-model-generator ↩
5. PixelDojo News. "Hyper3D's Rodin Gen-2: Revolutionizing 3D Model Generation for Professional Creators." October 2025. https://pixeldojo.ai/industry-news/hyper3ds-rodin-gen-2-revolutionizing-3d-model-generation-for-professional-creators ↩
6. Animation World Network. "Beyond Generation: Hyper3D.AI CTO Zhang Qixuan on Rodin Gen-2 Edit and the Future of 3D AI Workflows." 2026. https://www.awn.com/animationworld/beyond-generation-hyper3dai-cto-zhang-qixuan-rodin-gen-2-edit-and-future-3d-ai ↩
7. gaga.art. "Rodin Gen-2 Review 2026: The AI Image to 3D Revolution." 2026. https://gaga.art/blog/rodin-gen-2-review/ ↩
8. befores and afters. "Everything you need to know about Hyper3d.ai and its Rodin 3D generative AI model." 27 January 2026. https://beforesandafters.com/2026/01/27/everything-you-need-to-know-about-hyper3d-ai-and-its-rodin-3d-generative-ai-model/ ↩
9. Press Advantage. "Deemos Tech Launches Hyper3D Rodin, a Breakthrough Native 3D AI Model Generator." 8 May 2025. https://pressadvantage.com/story/77793-deemos-tech-launches-hyper3d-rodin-a-breakthrough-native-3d-ai-model-generator ↩
10. Deemos Tech on X. "Rodin Gen-1 open trials announcement." 30 May 2024. https://x.com/DeemosTech/status/1796243034872729618 ↩
11. Deemos Tech on X. "BANG voted Top 10 SIGGRAPH presentation." August 2025. https://x.com/DeemosTech/status/1955649365835714807 ↩
12. Naveen Manwani on X. "SIGGRAPH 2025 Paper Alert: BANG: Dividing 3D Assets via Generative Exploded Dynamics." 2025. https://x.com/NaveenManwani17/status/1951697766733779354 ↩
13. SIGGRAPH 2025 papers index, real time rendering. https://www.realtimerendering.com/kesen/sig2025.html ↩
14. Hyper3D by Deemos. Official website. https://hyper3d.ai ↩
15. Hyperhuman Deemos. Rodin product page. https://hyperhuman.deemos.com/rodin
16. WaveSpeedAI Blog. "Introducing Hyper3d Rodin V2 Text To 3d on WaveSpeedAI." 2025. https://wavespeed.ai/blog/posts/introducing-hyper3d-rodin-v2-text-to-3d-on-wavespeedai/ ↩
17. WaveSpeedAI Blog. "Introducing Hyper3d Rodin V2 Image To 3d on WaveSpeedAI." 2025. https://wavespeed.ai/blog/posts/introducing-hyper3d-rodin-v2-image-to-3d-on-wavespeedai/ ↩
18. 3printr. "Hyper3D: Chinese AI 3D model platform secures millions in Series A round funding." 2025. https://www.3printr.com/hyper3d-chinese-ai-3d-model-platform-secures-millions-in-series-a-round-funding-3276516/ ↩
19. CB Insights. "Deemos company profile." https://www.cbinsights.com/company/deemos ↩
20. SIGGRAPH 2025 conference. "3D Generative AI Transforms How We Create, Design, Interact With Digital Content." https://s2025.siggraph.org/3d-generative-ai-transforms-how-we-create-design-interact-with-digital-content/
21. Press Advantage. "Hyper3D Launches Rodin Gen-2.5, Bringing Sculpt-Level Detail and Production Control to AI 3D Generation." 26 May 2026. https://pressadvantage.com/story/94732-hyper3d-launches-rodin-gen-2-5-bringing-sculpt-level-detail-and-production-control-to-ai-3d-generati ↩
22. Press Advantage via Barchart. "Hyper3D Featured in NVIDIA Case Study on Lowe's 3D Asset Generation Workflow." 24 April 2026. https://www.barchart.com/story/news/1503514/hyper3d-featured-in-nvidia-case-study-on-lowes-3d-asset-generation-workflow ↩
23. Hyper3D by Deemos. "Pricing Plans for AI 3D Generation." https://hyper3d.ai/pricing ↩