Video · image-to-video · video-generation

MAGI-1

sand-ai

Added as a high-priority open video generation candidate with Apache-2.0 HF metadata.

Integrated独立环境源码已固定magi-1

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magi-official-cu124

设备CUDA 12.4

worldfoundry-eval evaluate \
  --mode model \
  --model-id magi-1 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/magi-1 \
  --metric artifact_count \
  --json

兼容性与版本

由 Manifest 生成

集成状态: integrated
Runner 证据: 未记录
环境: magi-official-cu124
Python: 3.10.12
CUDA: CUDA 12.4
PyTorch: —
源码 revision: 6ff822e74ded50611e81e1d0e115146b5c4dd2a5
Checkpoint revision: cd0a46589f3279a3c5c579f5f3c693a6ad36d0d4

Runtime profile: magi-1
Pipeline binding: magi-1
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.video_official.pipeline_official_video:MAGI1Pipeline
Backend stage: official_runtime_bridge
Runtime 状态: integrated_checkpoint_required
Driver 状态: compatible
环境类型: 独立环境

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 magi-1

依赖版本约束 18

accelerate==0.32.1
beautifulsoup4==4.13.4
debugpy==1.8.14
diffusers==0.29.2
einops>=0.6.0
ffmpeg-python
ftfy==6.2.0
gpustat==1.1.1
imageio==2.34.0
imageio[ffmpeg]
matplotlib==3.10.1
numpy==1.26.4
protobuf==5.28.3
rich==14.0.0
sentencepiece==0.2.0
timm==1.0.15
torchdiffeq==0.2.4
transformers==4.42.3

Conda 依赖 7

python=3.10.12
pip
ffmpeg=4.4
pytorch==2.4.0
torchvision==0.19.0
torchaudio==2.4.0
pytorch-cuda=12.4

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 magi-1 --check-local --json

sand-ai/MAGI-1

Revision: cd0a46589f3279a3c5c579f5f3c693a6ad36d0d4
License: apache-2.0
Gated: false
Private: false

sand-ai/MAGI-1

Revision: —
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 magi-1 \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/magi-1 \
  --metric artifact_count \
  --json

输入契约

字段	已记录契约
`prompt`	Required
`image`	Required

Artifact 契约

Artifact 类型	文件名 / 路径
`generated_video`	`magi-1.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: 未记录
原生 Demo 证据: pending
验证 Imports: torch, torchvision, flash_attn, flashinfer, diffusers, transformers, sentencepiece, torchdiffeq

配方溯源

worldfoundry/data/models/catalog/video/magi-1.yamlGitHub6ff822e74ded50611e81e1d0e115146b5c4dd2a5

构建运行命令

输入契约

Artifact 契约

相关配方