VEFX Reward 32B

--- license: apache-2.0 language: - en library_name: transformers base_model: Qwen/Qwen3-VL-32B-Instruct tags: - video - video-editing - reward-model - vlm - qwen3-vl pipeline_tag: video-classification --- # VEFX-Reward-32B **VEFX-Reward-32B** is the 32B-parameter variant of the VEFX-Reward family — a video editing quality reward model based on **Qwen3-VL-32B-Instruct**. It scores text-driven video edits on three dimensions on a 1–4 scale: | Dimension | What it measures | |---|---| | **IF** — Instructional Following | Does the edit accurately reflect the editing instruction? | | **RQ** — Render Quality | Visual clarity, temporal consistency, physical plausibility | | **EE** — Edit Exclusivity | Were only the intended regions modified, without side-effects? | - 📄 Paper: [VEFX-Bench](https://arxiv.org/abs/2604.16272) - 💻 Code: [Visko-Platform/VEFX-Bench](https://github.com/Visko-Platform/VEFX-Bench) - 🤗 Dataset: [xiangbog/VEFX-Bench](https://huggingface.co/datasets/xiangbog/VEFX-Bench) - 🤗 Smaller model: [xiangbog/VEFX-Reward-4B](https://huggingface.co/xiangbog/VEFX-Reward-4B) - 🏆 Leaderboard: [vefx-leaderboard.com](https://vefx-leaderboard.com/) ## Quick Start ```bash git clone https://github.com/Visko-Platform/VEFX-Bench.git cd VEFX-Bench pip install -e . ``` ```python from vefx_reward import VEFXReward model = VEFXReward("viskoplatform/VEFX-Reward-32B", device="cuda") scores = model.score( original_video="examples/sample_videos/object_removal_original.mp4", edited_video="examples/sample_videos/object_removal_edited.mp4", instruction="Remove the woman with the grey backpack walking on the right side of the frame.", ) print(scores) # {'IF': 3.69, 'RQ': 3.70, 'EE': 3.26, 'Overall': 10.65} ``` > **Hardware:** ~65 GB VRAM (bfloat16). Tested on a single NVIDIA H100 80 GB. ## Citation ```bibtex @article{gao2026vefx, title={VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects}, author={Gao, Xiangbo and Jiang, Sicong and Liu, Bangya and Chen, Xinghao and Yang, Minglai and Yang, Siyuan and Wu, Mingyang and Yu, Jiongze and Zheng, Qi and Wang, Haozhi and others}, journal={arXiv preprint arXiv:2604.16272}, year={2026} } ``` ## License Apache 2.0.

Source context: 119 downloads · 3 likes · Pipeline video-classification · Library transformers · Repo viskoplatform/VEFX-Reward-32B

Source context: 69 downloads · 3 likes · Pipeline video-classification · Library transformers · Repo viskoplatform/VEFX-Reward-32B