LingBot-World
Robotics modelOpen-weights interactive video world simulator built on Wan2.2 for camera- and action-conditioned rollout generation (16 FPS, minute-level horizon in v1; Apache-2.0 for v1 code and checkpoints, while separate v2 causal release is CC BY-NC-SA 4.0). [1] [2] [4] [5]
Setup & usage →CheckpointsModel hub / homepageGetting started
- For
- Embodied AI and world-model researchers; Robot learning simulation teams; Multi-GPU inference engineers [2] [4]
- Parameters
- 18,544,332,864 (~18.5B F32 parameters in lingbot-world-fast safetensors metadata [2] [3] [4]
- Embodiments
- Embodiment-agnostic egocentric / free-camera visual world simulator (conditioned on camera trajectories and action… [2] [4]
- Source rights
- Named licenses are documented by part. Includes noncommercial terms. Review licenses
Source researched · Not tested by us
Sources checked · Research details
Licenses & related hardware
- License
- Apache-2.0 (v1 inference repo); CC BY-NC-SA 4.0 (separate v2 repo) (noncommercial), Apache-2.0 (v1 base-cam & fast checkpoints); CC BY-NC-SA 4.0 (v2 checkpoints) (noncommercial), Apache-2.0 (v1 README) · Details by part
Overview
LingBot-World is an open-weights interactive video world simulator built on the Wan2.2 i2v-A14B image-to-video Diffusion Transformer architecture (paired with a T5 text encoder and video VAE). Rather than outputting physical robot joint commands, it generates future video frames conditioned on 6-DoF camera pose trajectories or discrete action strings (--action_path, --action_string, --allow_act2cam). [1] [2] [4]
Model card summary
- Architecture
Wan2.2-based image-to-video Diffusion Transformer (i2v-A14B task architecture with T5 text encoder and video VAE) conditioned on camera poses or discrete action strings for interactive long-horizon world simulation.
- Base model
Wan2.2 (Wan-Video/Wan2.2 i2v-A14B architecture)
- Parameter count
18,544,332,864 (~18.5B F32 parameters in lingbot-world-fast safetensors metadata; i2v-A14B MoE/DiT architecture; base-cam repo total 149.25 GB includes dual/unquantized components)
Exact tensor count for lingbot-world-fast verified via Hugging Face API safetensors metadata.
- Input modalities
- rgblanguage
Initial RGB image, text prompt, and camera pose trajectories or action strings (e.g., WASD / camera control; action-string conditioning noted in README).
- Output modalities
- video-frames
Generates 480P (480x832) and 720P (720x1280) interactive video rollouts at 16 FPS (up to 961 frames / ~1 minute).
- Action space
Camera pose trajectories (6-DoF camera extrinsics/intrinsics) and user-friendly discrete action strings (--action_path / --action_string / --allow_act2cam) conditioning future video frame generation rather than low-level robot joint torques.
- Control frequency
16 Hz (16 FPS video generation reported in model card)
Model card reports sub-1-second latency at 16 FPS for real-time interactive rollout.
- Trained / supported embodiments
- Embodiment-agnostic egocentric / free-camera visual world simulator (conditioned on camera trajectories and action strings)
- Training datasets
- Undisclosed / non-public pretraining video corpus (arXiv:2601.20540); camera poses estimated via ViPE in examples
Training datasets are not publicly released for download in the repository.
[4] · Editorial assessment
Checkpoints
| Checkpoint | Format | Size | Access | Pinned revision |
|---|---|---|---|---|
| robbyant/lingbot-world-base-cam (v1, Apache-2.0) | safetensors | 149.25 GB | open | 6fc824ffc338 |
| robbyant/lingbot-world-fast (v1 distilled, Apache-2.0) | safetensors | 74.18 GB | open | b7a1db2da9bd |
| robbyant/lingbot-world-v2-14b-causal-fast (v2, CC BY-NC-SA 4.0 noncommercial) | safetensors | 80.16 GB | open | 5c33dd40b213 |
robbyant/lingbot-world-fast reports 74,182,934,990 bytes (~74.18 decimal GB / 69.09 GiB) usedStorage in S003 and requires downloading base-cam first per S004.
Is this for you?
- Use cases
- Interactive camera- and action-conditioned rollout generation
- Long-horizon visual world simulation for robot learning
- Real-time fast rollout generation via distilled LingBot-World-Fast
- Known limitations
- Heavy multi-GPU compute requirement (8 GPUs with FSDP + Ulysses parallelism documented for default 480P/720P inference; 149.25 GB base-cam / 69.09 GB fast checkpoint footprint)
- Training datasets and training code are not released in the inference repository
- License split across generations: v1 (robbyant/lingbot-world and v1 checkpoints) is Apache-2.0, whereas v2 (robbyant/lingbot-world-v2 and v2 checkpoints) is strictly noncommercial CC BY-NC-SA 4.0
- Safety and limitations
- Outputs simulated video frames rather than closed-loop physical robot motor commands; editorial adoption caveat: supplied evidence does not establish physical accuracy.
- Strict version-dependent licensing and maintenance tradeoff: v1 code and weights are Apache-2.0 but v1 maintenance is discontinued (S004), while v2 code and weights are noncommercial CC BY-NC-SA 4.0.
- Training code and pretraining datasets are not publicly released; minimum per-GPU VRAM is unspecified (8-GPU torchrun command is an upstream reference workflow, not a verified minimum).
Compute & fine-tuning
- Inference compute
- Documented hardware: 8x multi-GPU node (torchrun --nproc_per_node=8 with FSDP + Ulysses)
- Precision:
bf16 - Reported latency: 1000 ms
- Edge / consumer capable: No
Model card reports latency under 1 second (<1000 ms) when producing 16 FPS; exact minimum VRAM per GPU not stated.
- Fine-tuning
- Supported: No
Public repository provides inference/rollout generation scripts only; training/fine-tuning scripts are not included.
[4] · Editorial assessment
- Host computer
Documented reference commands use 8 GPUs (torchrun --nproc_per_node=8, --ulysses_size 8, FSDP); community 4-bit quantized variant mentioned in README for limited VRAM.
- Operating system
- Linux
Inferred from documented Linux/CUDA Python environment and shell instructions.
[4] · Editorial assessment
- Skills
- Python
- PyTorch Distributed (torchrun / FSDP)
- Diffusers / Wan2.2 inference
Inferred from documented Python/PyTorch/CLI setup and training dependencies.
[4] · Editorial assessment
Setup & usage
Open the upstream getting-started guide [4] · Model card / documentation [1] [2]
- Clone robbyant/lingbot-world and install Wan2.2 dependencies
- Download robbyant/lingbot-world-base-cam or robbyant/lingbot-world-fast from Hugging Face
- Run torchrun --nproc_per_node=8 generate.py (or generate_fast.py) with --dit_fsdp --t5_fsdp --ulysses_size 8
Upstream-reported benchmarks
Upstream-reported only: Open Source Robotics has not run training, inference, or hardware evaluations for these benchmarks.
| Benchmark | Upstream-reported score | Scope & caveats |
|---|---|---|
| LingBot-World technical report evaluations (arXiv:2601.20540) | Upstream model card and README give 961 frames (~1 minute at 16 FPS) as an example setting conditional on sufficient CUDA memory, and report sub-1s latency. | Upstream-reported world-model metrics; not independently verified by OSR. |
Project notes
Visual simulation scope and multi-GPU compute requirements
LingBot-World is an embodiment-agnostic visual rollout simulator, not a closed-loop physical robot controller; as an editorial adoption caveat, the supplied evidence does not establish physical accuracy for generated video rollouts. Checkpoint storage requirements are large and additive for the distilled variant: robbyant/lingbot-world-fast reports 74,182,934,990 bytes of repository storage (~74.18 decimal GB / 69.09 GiB; 18,544,332,864 F32 parameters in safetensors metadata), and S004 instructs Fast users to download robbyant/lingbot-world-base-cam first and place the Fast weights inside that directory—so Fast's individual storage does not represent total setup storage or GPU memory. Upstream's documented inference workflow uses an 8-GPU node (torchrun --nproc_per_node=8 with FSDP and Ulysses parallelism) for 480P and 720P generation, with community 4-bit quantization noted separately; minimum per-GPU VRAM is unspecified in the supplied documentation, and 8 GPUs describes upstream reference commands rather than a verified minimum configuration. [2] [3] [4]
Upstream-reported world-model metrics
The model card and README describe an example setting of 961 frames (~1 minute at 16 FPS) conditional on sufficient CUDA memory, alongside sub-1s latency claims (linking to arXiv:2601.20540, which is not excerpted here). All reported horizon, frame-rate, and latency figures are upstream-reported; Open Source Robotics has not run inference or benchmarked LingBot-World on multi-GPU hardware. [2] [4]
What we checked
None. Prepared from public upstream sources without hands-on hardware execution.
Updates
- Upstream last updated
- Jul 9, 2026 [1]
- Latest release
- Apr 2, 2026 [3]
- Profile updated
- Nov 21, 2026
- Sources last checked
- Nov 21, 2026
- Next review
- May 21, 2027
- Reviewed revision
- robbyant/lingbot-world@a43bec7f8091c83e9b30b16b912f6fc906236fa6; HF lingbot-world-base-cam@6fc824ffc338d64c97c77e2eb8c0f4cfc24d82bd; HF lingbot-world-fast@b7a1db2da9bd3ba675ee01c228f41db0309b981e · software repository
Separate license matrix
Major 2026 open-weights interactive world simulator with Apache-2.0 v1 inference code and weights; marked include_partial because training code and pretraining datasets are not released and v2 switches to noncommercial CC BY-NC-SA 4.0.
| Layer | Availability / license |
|---|---|
| Code | available · Apache-2.0 (v1 inference repo); CC BY-NC-SA 4.0 (separate v2 repo) Verified directly in LICENSE.txt of both repositories: robbyant/lingbot-world is Apache-2.0; robbyant/lingbot-world-v2 is CC BY-NC-SA 4.0. Note: inference code only (no training code). [1] [5] |
| Model weights | available · Apache-2.0 (v1 base-cam & fast checkpoints); CC BY-NC-SA 4.0 (v2 checkpoints) Corrects preliminary audit note in candidates.json: v1 HF checkpoints (lingbot-world-base-cam, lingbot-world-fast) are Apache-2.0; only v2 checkpoints (e.g., lingbot-world-v2-14b-causal-fast) are CC BY-NC-SA 4.0. [2] [3] [5] |
| Training datasets | unavailable · License not fully assessed Pretraining video datasets are not publicly released; only small inference example assets are included in the repo. [4] |
| Documentation | available · Apache-2.0 (v1 README) [1] [4] |
Strict version split between v1 and v2 licenses and maintenance
Licensing and maintenance split strictly by version. The v1 repository (robbyant/lingbot-world) and v1 Hugging Face checkpoints (lingbot-world-base-cam and lingbot-world-fast) are licensed under Apache-2.0, verified in LICENSE.txt and Hub metadata. However, the reviewed v1 README (S004) explicitly states that robbyant/lingbot-world is no longer actively maintained and directs future development to LingBot-World-Infinity / v2 (robbyant/lingbot-world-v2 and robbyant/lingbot-world-v2-14b-causal-fast), which are licensed under noncommercial CC BY-NC-SA 4.0. Choosing permissive v1 weights therefore also means accepting discontinued v1 maintenance. In the reviewed v1 materials, only inference code and small example assets are published; training code and pretraining video datasets are not released there, and v2 training-artifact availability was not verified in this review. [1] [2] [3] [4] [5]
References
Each source links to the exact revision we read. “Used for” shows where this page relies on it.
- S001 robbyant/lingbot-world GitHub metadata, HEAD commit, and LICENSE.txt
Default branch main HEAD is a43bec7f8091c83e9b30b16b912f6fc906236fa6 (2026-07-09T10:39:38Z); LICENSE.txt is Apache License Version 2.0.Revision, date & where cited
robbyant (GitHub) · github.com · revision
a43bec7· GitHub API repos/robbyant/lingbot-world & LICENSE.txt at commit a43bec7f8091 · Accessed Nov 21, 2026
Used for: Overview, Is this for you?, Setup & usage, What we checked and 1 more - S002 Hugging Face model card and API metadata: robbyant/lingbot-world-base-cam
149.25 GB total, ungated, license: apache-2.0, lastModified 2026-02-02; reports 16 FPS with <1s latency and minute-level horizon.Revision, date & where cited
robbyant (Hugging Face) · huggingface.co · HF API & README.md at revision 6fc824ffc338 · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Checkpoints, Is this for you? and 6 more - S003 Hugging Face API metadata: robbyant/lingbot-world-fast
18,544,332,864 F32 parameters, 69.09 GB safetensors, ungated, license: apache-2.0, lastModified 2026-04-02.Revision, date & where cited
robbyant (Hugging Face) · huggingface.co · HF API /api/models/robbyant/lingbot-world-fast · Accessed Nov 21, 2026
Used for: Model card summary, Checkpoints, Is this for you?, Visual simulation scope and multi-GPU compute requirements and 2 more - S004 robbyant/lingbot-world README.md at pinned commit
Built on Wan2.2 (i2v-A14B), 480P & 720P 8-GPU FSDP/Ulysses inference, action_string & camera conditioning, community 4-bit quantized note.Revision, date & where cited
robbyant (GitHub) · github.com · revision
a43bec7· README.md at commit a43bec7f8091 · Accessed Nov 21, 2026
Used for: Overview, Model card summary, Is this for you?, Compute & fine-tuning and 5 more - S005 robbyant/lingbot-world-v2 LICENSE.txt and HF v2-14b-causal-fast metadata
Confirms v2 repository and robbyant/lingbot-world-v2-14b-causal-fast (80.16 GB) are licensed under CC BY-NC-SA 4.0 (noncommercial).Revision, date & where cited
robbyant (GitHub / Hugging Face) · github.com · revision
1895d30· GitHub commit 1895d300d8ac & HF revision 5c33dd40b213 · Accessed Nov 21, 2026
Used for: Checkpoints, Is this for you?, Separate license matrix
Correction guidance · Discussion is not enabled · Profile format 0.8.0-draft.1
Change history
2026-11-21 — Initial 0.8.0-draft.1 model draft prepared from pinned GitHub commits a43bec7f8091 (v1) & 1895d300d8ac (v2) and HF revisions 6fc824ffc338 / b7a1db2da9bd / 5c33dd40b213.