Model reference · open weights

optical-flow-MEMFOF-Tartan-T-TSKH

Available as managed deployment Image egorchistov · community Image edit 1 variants 5k dl/mo

optical-flow-MEMFOF-Tartan-T-TSKH is an open-weight image model from egorchistov. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byegorchistov
TypeImage models
TaskImage edit
Parameters (lead)76M
Runs withpytorch
Based onegorchistov/optical-flow-MEMFOF-Tartan-T
Released2025-06-02
Popularity5k downloads / month
LicenceOpen weights

About

What optical-flow-MEMFOF-Tartan-T-TSKH is

🔍 MEMFOF is a memory-efficient optical flow method for Full HD video that combines high accuracy with low VRAM usage.

Note: This particular checkpoint is intended for real-world videos — it is trained with higher diversity and robustness in mind.

Read the full model card

🛠️ Usage

Install MEMFOF via the package manager:

pip3 install git+https://github.com/msu-video-group/memfof

Then use the following snippet to compute backward and forward optical flow for three consecutive frames:

import torch
from memfof import MEMFOF

device = "cuda" if torch.cuda.is_available() else "cpu"
model = MEMFOF.from_pretrained("egorchistov/optical-flow-MEMFOF-Tartan-T-TSKH").eval().to(device)

with torch.inference_mode():
    # [B=1, T=3, C=3, H=1080, W=1920]
    example_input = torch.randint(0, 256, [1, 3, 3, 1080, 1920], device=device)
    # [B=1, C=2, H=1080, W=1920]
    backward_flow, forward_flow = model(example_input)["flow"][-1].unbind(dim=1)

📚 Citation

@article{bargatin2025memfof,
  title={MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation},
  author={Bargatin, Vladislav and Chistov, Egor and Yakovenko, Alexander and Vatolin, Dmitriy},
  journal={arXiv preprint arXiv:2506.23151},
  year={2025}
}

From the published model card. Full card on the HuggingFace links in the sidebar.

How it works

How image models work

Text promptwhat to makeText encoderunderstands itDiffusion stepsdenoise to pixelsImagePNG / JPEGA diffusion model starts from noise and denoises it, guided by your prompt, into a finished image.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys optical-flow-memfof-tartan-t-tskh for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (optical-flow-memfof-tartan-t-tskh below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"optical-flow-memfof-tartan-t-tskh","prompt":"a red bicycle","size":"1024x1024"}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms