{"id":"weviscut","slug":"weviscut","name":"WeVisCut","orgId":"tencent","family":"weviscut","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":9000000000,"paramsSource":"slug","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://arxiv.org/abs/2610.38352","hfRepo":null,"modalities":["text","video"],"aliases":["WeVisCut","weviscut","weviscut-9b","weviscut 9b","tencent/weviscut","wechat vision weviscut"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-11-01","announced":"2026-10-28","blurb":"Tencent WeChat Vision's 9B tool-using agent model for video editing, fine-tuned from Qwen3.5-9B with Xidian University co-authors. Given a knowledge article or narration script, it builds a multi-minute edited video one tool call at a time. Its 12 tools cover planning, narration, asset retrieval, templates, composition, music, inspection, repair and stitching. It is not a text-to-video generator: it needs Tencent's WeVisCut runtime, which runs the tool calls. Weights on Hugging Face; the GitHub license file says Apache-2.0.","api":"none","openWeights":"yes","params":{"text":"About 9.41B (9,409,813,744 BF16 parameters in the merged checkpoint)","source":"Hugging Face safetensors metadata for tencent/WeVisCut"},"facts":[{"label":"Type","value":"Agentic video editing: a policy model that emits one tool call per step (about 12 per run) and a runtime that executes them; not a standalone text-to-video model"},{"label":"Base model","value":"Qwen/Qwen3.5-9B, fine-tuned by Tencent (per the Hugging Face card and the GitHub LICENSE)"},{"label":"Task","value":"A knowledge article or narration script in, a multi-minute edited video out"},{"label":"Tools","value":"12 editing tools: segment, plan, TTS, retrieval, template, compose, BGM, judge, reflect, probe and stitch, run by the WeVisCut Studio runtime with an editable timeline"},{"label":"Training","value":"Editing inversion and verified replay on 3,750 finished videos yield 134,771 training examples; SFT and runtime-verified RFT, then Guided-OPD and RCF-DAPO"},{"label":"Weights","value":"Hugging Face tencent/WeVisCut, not gated: a merged BF16 checkpoint plus a LoRA adapter"},{"label":"License","value":"The GitHub LICENSE says Apache-2.0 for WeVisCut's code, parameters and weights, with Qwen3.5-9B (Apache-2.0) and other third-party components under their own terms. The Hugging Face repo has no LICENSE file; its card is tagged other and says only that the code is Apache-2.0, with weights and third-party components under their respective terms"},{"label":"Code","value":"GitHub Tencent/WeVisCut: the Studio runtime, the 12-tool harness and the trajectory-construction pipeline"},{"label":"Requirements","value":"Python 3.11 or later and an NVIDIA GPU with about 24 GB for the BF16 model; TTS, retrieval and rendering services are configured separately"},{"label":"API","value":"None stated; run locally"},{"label":"Authors","value":"Chenyu Mu, Wenming Weng, Qinrui Wang, Xingsong Ye, Hao Yu, Jun He, Chong Sun, Chen Li, Jing Lyu, Erkun Yang and Cheng Deng (Xidian University; WeChat Vision, Tencent)"}],"claims":["Lab claim: 90.5 overall on Tencent's 100-task script-to-video benchmark (five runs), against 89.9 for Claude Opus 5, 84.6 for Gemini 3.1 Pro and 74.5 for its Qwen3.5-9B base, in the same tool environment.","Lab claim: about 33x fewer generated tokens and 73.3% fewer tool calls than Claude Opus 5 per successful output minute.","Lab claim: +6.8 SCF over Crayotter and +10.0 over VideoAgent, running 4.1x and 5.0x faster at 10.8x and 6.4x lower cost, with human raters preferring it (4.56 vs 3.48 overall)."],"sources":[{"kind":"paper","title":"WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video (arXiv)","url":"https://arxiv.org/abs/2610.38352","date":"2026-10-28"},{"kind":"lab","title":"WeVisCut project page (WeChat Vision, Tencent)","url":"https://tencent.github.io/WeVisCut/"},{"kind":"repo","title":"Tencent/WeVisCut on GitHub","url":"https://github.com/Tencent/WeVisCut"},{"kind":"repo","title":"tencent/WeVisCut on Hugging Face","url":"https://huggingface.co/tencent/WeVisCut"},{"kind":"repo","title":"WeVisCut LICENSE (GitHub)","url":"https://github.com/Tencent/WeVisCut/blob/main/LICENSE"},{"kind":"press","title":"Machine Delusions post on X","url":"https://x.com/Machinedelusion/status/2116668287656333409","date":"2026-10-31"}],"firstBenchmark":null},"organization":{"id":"tencent","name":"Tencent","slug":"tencent","country":null,"url":null,"color":"#A39E8F","mark":"TE"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 28, 2026; no independent results yet.","lead":"As of Nov 3, 2026, WeVisCut is pending benchmarks on isitsota: announced Oct 28, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}