Downloads · 30 days
0
Pensioner/ShotPlan-Wan2.2-T2V-A14B-HighNoise
ShotPlan-Wan2.2-T2V-A14B-HighNoise is a text-to-video model from Pensioner. Use it when you need video from a text prompt. It is set up for wan2.2. The card lists the license as apache-2.0.
<p align="center" <a href="https://pensioner-11.github.io/ShotPlan/"<b🌐 Project Page</b</a · <a href="https://arxiv.org/abs/2607.17675"<b📄 Paper</b</a · <a href="https://github.com/Pensioner-…
Downloads · 30 days
0
Access
Public
Updated Jul 22, 2026
Repo size
85.7 GB
Likes
5
Public
Click a slice to open those files.
.safetensors28.6 GB · 100%
From the Hugging Face model README
Fine-tuned high-noise expert of Wan2.2-T2V-A14B for ShotPlan: Cinematic Video Generation with Learnable Planning Token — controllable multi-shot video generation with hard cuts at user-specified frame indices.
ShotPlan-Wan2.2-T2V-A14B-HighNoise.safetensors — full state dict of the fine-tuned high-noise DiT (step 3000), containing:
hardcut_embedding [1, 1, 5120] — the learnable planning token.Only the high-noise expert is fine-tuned: shot structure is decided early in the denoising trajectory. At inference the low-noise expert runs with the original Wan2.2 weights and the stock model function; a router injects planning tokens only into the high-noise expert.
This checkpoint requires the ShotPlan inference code (planning-token injection + fractional temporal RoPE). It is not a drop-in diffusers checkpoint.
git clone https://github.com/Pensioner-11/ShotPlan.git && cd ShotPlan
pip install -r requirements.txt
huggingface-cli download Wan-AI/Wan2.2-T2V-A14B --local-dir ./models/Wan2.2-T2V-A14B
huggingface-cli download Pensioner/ShotPlan-Wan2.2-T2V-A14B-HighNoise --local-dir ./models/shotplan_wan22
python inference/infer_wan22.py \
--wan22_root ./models/Wan2.2-T2V-A14B \
--ckpt ./models/shotplan_wan22/ShotPlan-Wan2.2-T2V-A14B-HighNoise.safetensors \
--prompt "Global scene description. Shot 1: ... Shot 2: ..." \
--cut_at 40 \
--output_dir ./results
--cut_at takes comma-separated frame indices (81-frame video @ 16 fps). Internally the script registers hardcut_embedding on the high-noise DiT, loads this state dict, and injects one planning token per cut at fractional RoPE coordinate t = 1 + frame/4.
Fine-tuned from Wan2.2-T2V-A14B high-noise expert on 6.4K multi-shot samples (480×832, 81 frames) with learning rate 1e-5, timestep boundary restricted to the high-noise segment (max_timestep_boundary 0.358). The planning token and DiT weights are optimized jointly. See the code repository for the exact training script.
Apache-2.0, inherited from Wan2.2.
@article{guo2026shotplan,
title={ShotPlan: Cinematic Video Generation with Learnable Planning Token},
author={Guo, Su and Liu, Guangce and Yang, Haosen and Wang, Jiepeng and Liu, Cong and Liu, Junqi ... Zhang, Chi and Li, Xuelong},
journal={arXiv preprint arXiv:2607.17675},
year={2026}
}