Skip to content
Other

Gen4P

adapting video generators for 4D perception

1 min readupdated

Gen4P turns a video generator into a tool for full 4D scene perception. The model handles 3D point tracking, video depth estimation, camera pose estimation, and dense 4D visualization. The architecture combines a Wan2.1 video foundation, a frozen DVD depth prior module, and a query decoder. This solution is ideal for researchers and developers working with computer vision and video analysis.

Key features

  • Built on the Wan2.1 video generator
  • Supports 3D point tracking in video
  • Includes a DVD depth prior module
  • Enables camera pose estimation

What you can do

  • Run point tracking to analyze motion in videos
  • Perform frame depth estimation to build 3D structures
  • Determine camera motion trajectories and poses in video

Example

hf download yitongx/Gen4P gen4p.pth --local-dir ckpt
hf download FayeHongfeiZhang/DVD dvd_1.1.safetensors --local-dir ckpt
Read moreDetails
License: CC BY-NC 4.0
Base model: Wan2.1
Components: Wan2.1, DVD depth prior, query decoder
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 3.3 GB · ready files4.1 GB
  • FP8 / INT8recommendedweights 1.6 GB2.3 GB
  • 4-bitweights 0.9 GB1.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # yitongx/Gen4P
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download yitongx/Gen4P --local-dir ~/models/Gen4P
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to Gen4P
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Gen4P (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

yitongx/Gen4P
Author
yitongx
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments