lingbot-worl

<p align="center"> <img src="assets/worl-teaser.webp" width="100%" alt="WoRL long-horizon generations and RL system efficiency"> </p> <div align="center">

LingBot WoRL

A policy checkpoint from the All-in-One RL Framework of Video World Model

WoRL · Base model · WBench rollouts · RevBench rollouts

</div>

LingBot WoRL is the camera-conditioned policy checkpoint produced by the WoRL reinforcement-learning framework for LingBot-World-Fast. It keeps the base model's first-image, text, framewise camera-pose, and camera-intrinsics interface while improving the policy through long-horizon video RL.

The same policy is released in two forms: a compact PEFT LoRA adapter and a standalone BF16 transformer with the adapter already merged.

WoRL in one figure

<p align="center"> <img src="assets/worl-framework.png" width="100%" alt="WoRL reinforcement-learning framework"> </p>

WoRL brings together efficient on-policy video training, a history-aware Next Video Reward Model (NVRM), and a revisiting-centered environment. Candidate continuations are generated from an autoregressive rollout context, ranked by NVRM, and used by the policy update while the reference policy supplies KL regularization.

Release overview

Repository layout

The text encoder, tokenizer, VAE, scheduler, and complete LingBot runtime are not duplicated here. They remain required from the compatible base release.

Load the policy

Option A · LoRA adapter

Use this form when the compatible LingBot-World-Fast base is already available.

import torch
from peft import PeftModel
from wan.modules.model_fast import WanModelFast

base = WanModelFast.from_pretrained(
    "robbyant/lingbot-world-fast",
    torch_dtype=torch.bfloat16,
    control_type="cam",
)
model = PeftModel.from_pretrained(
    base,
    "qyoo/lingbot-worl",
    is_trainable=False,
)
model.eval()

Option B · Merged transformer

Use this form to avoid adapter attachment at inference time.

import torch
from wan.modules.model_fast import WanModelFast

model = WanModelFast.from_pretrained(
    "qyoo/lingbot-worl",
    subfolder="merged",
    torch_dtype=torch.bfloat16,
    control_type="cam",
)
model.eval()

For full image-to-video generation, insert either transformer form into the compatible LingBot-World-Fast pipeline and supply its remaining base-model components.

Input contract

The evaluated runtime generates 81-frame clips with an 80-frame stride at 16 FPS, preserving one shared boundary frame between adjacent clips.

Evaluation artifacts

The linked private datasets are self-contained WoRL rollout packages. Each includes generated videos, exact first images, prompts, camera controls, seeds, per-rollout scores, per-case scores, manifests, and SHA-256 integrity lists.

WBench v1 · 158 cases × 3 seeds

RevBench · 150 cases × 3 seeds

These values are read directly from the two published result packages. The RevBench package contains WoRL outputs only.

Export integrity

• Adapter: 800 BF16 tensors across 400 LoRA layers, rank / alpha 128 / 128.
• Adapter SHA-256: a14c4275131a98b6bad24aa09ab54a2982c7fed4407bf084a57e582482840648.
• Merged transformer: 18,544,332,864 parameters and 1,421 BF16 state tensors.
• Merge method: peft.PeftModel.merge_and_unload(safe_merge=True).
• Six sampled layers spanning blocks 0–39 matched independently computed base-plus-LoRA weights before and after serialization and reload.
• The standalone model reloaded with WanModelFast.from_pretrained, moved to an NVIDIA H100, and contained no remaining lora_ state keys.

Limitations and responsible use

Long autoregressive rollouts can still accumulate temporal artifacts, identity drift, geometric inconsistency, prompt mismatch, and camera-motion error. Generated video is synthetic and must not be treated as factual simulation or used as an autonomous-control signal. Users should review outputs, respect rights and consent for input media, and add safeguards appropriate to the downstream application.

License

This repository is released under Apache 2.0. The LingBot-World-Fast base model and runtime remain subject to their upstream terms and notices.