World models · image-to-video · camera-controlled-video · interactive-world-model · long-video-generation

AlayaWorld

LTX-2.3 World Models

The runtime reuses WorldFoundry's existing LTX-2.3 Transformer, VAE, Gemma connector, RoPE, patchifier, attention dispatcher, and distributed helpers.

Integrated统一环境源码已固定alayaworld

构建运行命令

选择仓库中已记录的 variant，然后复制对应的准备、检查或运行命令。

worldfoundry.pipeline

Variant

任务image-to-video

环境worldfoundry-unified-cu128

设备CUDA 12.8

worldfoundry-eval evaluate \
  --mode model \
  --model-id alayaworld \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/alayaworld \
  --metric artifact_count \
  --json

兼容性与版本

由 Manifest 生成

集成状态: integrated
Runner 证据: checkpoint gpu validated
环境: worldfoundry-unified-cu128
Python: 3.11
CUDA: CUDA 12.8
PyTorch: torch>=2.6
源码 revision: 58678a00eb6fde0a77206b7466c65ab622acfeb9
Checkpoint revision: e3f1adebec5cda1c77c55c115cde47fba279f887

Runtime profile: alayaworld
Pipeline binding: alayaworld
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.alayaworld.pipeline_alayaworld:AlayaWorldPipeline
Backend stage: independent_in_tree_runtime
Runtime 状态: checkpoint_gpu_validated_official_case1_single_chunk
Driver 状态: compatible
环境类型: 统一环境

安装环境

环境解析器会读取已记录 profile，并选择此处显示的统一或独立环境。

bash scripts/setup/model_env_install.sh --model alayaworld

依赖版本约束 20

torch>=2.6
torchvision
transformers>=4.49
tokenizers>=0.20.3
safetensors
huggingface-hub
accelerate
sentencepiece
einops
numpy
scipy
pillow
opencv-python
imageio
imageio-ffmpeg
av
omegaconf
easydict
tqdm
torchao

Conda 依赖 4

python
pip
ffmpeg
ninja

Checkpoint 与资产

分配算力前先做本地检查；gated、private 与 license 字段直接来自 checkpoint manifest。

worldfoundry-eval zoo model-download --model-id alayaworld --check-local --json

AlayaLab/AlayaWorld

Revision: e3f1adebec5cda1c77c55c115cde47fba279f887
License: —
Gated: —
Private: —

google/gemma-3-12b-it-qat-q4_0-unquantized

Revision: 68f7ee4fbd59087436ada77ed2d62f373fdd4482
License: —
Gated: true
Private: —

depth-anything/DA3NESTED-GIANT-LARGE-1.1

Revision: b2359bdf726fb44ef62acca04d629dcf158053e7
License: —
Gated: —
Private: —

运行与输出

生成的命令通过共享 evaluation 边界运行，并持久保存结果 manifest 与 artifact。

worldfoundry-eval evaluate \
  --mode model \
  --model-id alayaworld \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/alayaworld \
  --metric artifact_count \
  --json

输入契约

字段	已记录契约
`prompt`	Required
`image`	Required
`video`	Optional
`actions`	camera_trajectory, camera_path

Artifact 契约

Artifact 类型	文件名 / 路径
`generated_world_video`	`—`
`generated_world`	`alayaworld.mp4`

证据与来源

Catalog 集成、原生 demo parity 与 runner parity 是三条独立记录。

集成状态: integrated
Runner 证据: checkpoint gpu validated
原生 Demo 证据: 未记录
验证 Imports: torch, torchvision, transformers, safetensors, einops, cv2, worldfoundry.base_models.diffusion_model.video.ltx2.alayaworld, worldfoundry.base_models.three_dimensions.depth.depth_anything.depth_anything_v3.api, worldfoundry.synthesis.visual_generation.alayaworld

配方溯源

worldfoundry/data/models/catalog/world_models/alayaworld.yamlProjecthttps://alaya-lab.github.io/AlayaWorld/Paperhttps://arxiv.org/abs/2607.06291GitHub58678a00eb6fde0a77206b7466c65ab622acfeb9Hugging Facee3f1adebec5cda1c77c55c115cde47fba279f887

构建运行命令

输入契约

Artifact 契约

相关配方