Video · text-to-video · image-to-video

HunyuanVideo 1.5

tencent

Added as a high-priority current open-weight video model. Native T2V and I2V infer-only `generate.py` paths are now ported in-tree and release-validation verified with local checkpoint assets.

Runner verified统一环境源码已固定hunyuanvideo-1.5

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text-to-video

环境worldfoundry-unified-cu128

设备CUDA 12.8

worldfoundry-eval evaluate \
  --mode model \
  --model-id hunyuanvideo-1.5-t2v \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/hunyuanvideo-1.5-t2v \
  --metric artifact_count \
  --json

兼容性与版本

由 Manifest 生成

集成状态: integrated
Runner 证据: verified
环境: worldfoundry-unified-cu128
Python: 3.11
CUDA: CUDA 12.8
PyTorch: torch
源码 revision: 60783e704160023913bee78f0b47036d393d4dfa
Checkpoint revision: 9b49404b3f5df2a8f0b31df27a0c7ab872e7b038

Runtime profile: hunyuanvideo-1.5-t2v
Pipeline binding: hunyuanvideo-1.5
Runner: worldfoundry.pipeline
Pipeline target: worldfoundry.pipelines.video_official.pipeline_official_video:HunyuanVideo15T2VPipeline
Backend stage: official_runtime_bridge
Runtime 状态: integrated_checkpoint_required
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 hunyuanvideo-1.5-t2v

依赖版本约束 11

torch
torchvision
diffusers>=0.35.0
transformers>=4.57.1
accelerate
peft>=0.17.0
safetensors
imageio
imageio-ffmpeg
opencv-python
sentencepiece

Conda 依赖 3

python
pip
ffmpeg

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 hunyuanvideo-1.5 --check-local --json

tencent/HunyuanVideo-1.5

Revision: 9b49404b3f5df2a8f0b31df27a0c7ab872e7b038
License: other
Gated: false
Private: false

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 hunyuanvideo-1.5-t2v \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/hunyuanvideo-1.5-t2v \
  --metric artifact_count \
  --json

输入契约

字段	已记录契约
`prompt`	Required
`image`	Optional
`video`	Optional
`actions`	seed

Artifact 契约

Artifact 类型	文件名 / 路径
`generated_video`	`hunyuanvideo-1.5-t2v.mp4`
`expected artifact`	`hunyuanvideo15_t2v_native_seed42_848x480_9f.mp4`
`expected artifact`	`hunyuanvideo15_t2v_worldfoundry_seed42_848x480_9f.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: verified
原生 Demo 证据: verified
验证 Imports: torch, diffusers, transformers, peft

配方溯源

worldfoundry/data/models/catalog/video/hunyuanvideo-1.5.yamlGitHub60783e704160023913bee78f0b47036d393d4dfa

构建运行命令

输入契约

Artifact 契约

相关配方