Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
[project]
name = "looking-ahead"
version = "0.1.0"
description = "Future Chunk Prediction and Teacher Forcing for causal video diffusion"
readme = "README.md"
requires-python = ">=3.12"
license = "Apache-2.0"
dependencies = [
"torch==2.10.0",
"torchvision==0.25.0",
"torchcodec==0.10.0",
"accelerate>=1.13.0",
"diffusers>=0.37.1",
"transformers>=5.5.3",
"flash-attn-4>=4.0.0b5",
"einops>=0.8.2",
"ftfy>=6.3.1",
"huggingface-hub>=1.10.1",
"matplotlib>=3.10.8",
"numpy>=1.26.4",
"omegaconf>=2.3.0",
"pillow>=10.0.0",
"regex>=2024.0.0",
"safetensors>=0.4.3",
"sentencepiece>=0.2.1",
"tokenizers>=0.22.2",
"tqdm>=4.67.3",
"wandb>=0.25.1",
"webdataset>=1.0.2",
]
[project.optional-dependencies]
dev = ["pytest>=8.0.0", "ruff>=0.6.0"]
[[tool.uv.index]]
name = "pytorch-cu128"
url = "https://download.pytorch.org/whl/cu128"
explicit = true
[tool.uv.sources]
torch = { index = "pytorch-cu128" }
torchvision = { index = "pytorch-cu128" }
[tool.ruff]
line-length = 100
target-version = "py312"
extend-exclude = ["src/wan", "src/wan22"]
[tool.ruff.lint]
select = ["E", "F", "I", "B", "C4", "UP", "W"]
ignore = ["E501"]