Downloads · 30 days
5
8% of all-time downloads
noctuashap/trackwan-1.3b-bidir-merged-bias
trackwan-1.3b-bidir-merged-bias is a image-to-video model from noctuashap. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
A track-conditioned finetune of Wan2.1-Fun-1.3B (InP) for image-to-video generation with MotionStream-style point-track motion control. This is the mergedbias bidirectional training run, checkpoint 4800.
Downloads · 30 days
5
8% of all-time downloads
All-time downloads
64
Public
Parameters
1.6B
3.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.1 GB · 100%
From the Hugging Face model README
A track-conditioned finetune of Wan2.1-Fun-1.3B (InP) for image-to-video generation
with MotionStream-style point-track motion control. This is the merged_bias bidirectional
training run, checkpoint 4800.
Wan-AI/Wan2.1-Fun-1.3B-InP (Apache-2.0)transformer/model.safetensors, ~2.9 GB). Text encoder / VAE are the standard Wan components.This is not a vanilla diffusers pipeline — the track-conditioning is a custom WanTrack
architecture. Load it with the FastVideo fork that produced it, e.g.:
# in the FastVideo repo, using the trackwan inference helper
import data_pipeline.trackwan_infer as twi
model, cfg = twi.load_trackwan("<this repo checked out>", "<train yaml>")
Pair it with the base Wan2.1-Fun-1.3B-InP text encoder + VAE. See the FastVideo project for the exact config/YAML and track-conditioning input format (per-frame point tracks + visibility).
model.safetensors — trained transformer weights (bf16).config.json — transformer architecture config.Apache-2.0, inherited from the Wan base model.