{"id":"sensenova-6-8-code2video","slug":"sensenova-6-8-code2video","name":"SenseNova 6.8 Code2Video","orgId":"sensetime","family":"sensenova-6-8-code2video","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/SenseTime_AI/status/2115445835068748044","hfRepo":null,"modalities":["text","image","video"],"aliases":["SenseNova 6.8 Code2Video","sensenova-6.8-code2video","sensenova 6.8 code2video","sensenova code2video","code2video","sensenova/sensenova-6.8-code2video"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-28","announced":"2026-10-28","blurb":"SenseTime's open model for code-driven video creation: rather than generating pixels, it writes executable animation code, renders it into a short video, reviews the frames and revises, over long agent runs in Claude Code. Fine-tuned from Qwen3.8-27B. Released with its production skill, prompt templates and example trajectories; Apache-2.0 weights on Hugging Face.","api":"none","openWeights":"yes","params":{"text":"27B (Qwen3.8-27B base; 27.36B in the safetensors)","source":"SenseNova Hugging Face model card and safetensors metadata"},"facts":[{"label":"Base model","value":"Qwen3.8-27B (fine-tune)"},{"label":"Type","value":"Vision-language model that writes and renders code to make short videos; it does not generate video pixels directly"},{"label":"Workflow","value":"A general model expands the prompt; Code2Video then builds the film in Claude Code with SenseTime's code-video skill and can apply revision notes"},{"label":"Context","value":"512K tokens (524,288) in the recommended serving setup"},{"label":"Released with","value":"Production skill and prompt templates on GitHub (OpenSenseNova/SenseNova-6.8-Code2Video) and example production trajectories with 357 figures"},{"label":"Weights","value":"Published on Hugging Face under Apache-2.0 (sensenova org: repo created Oct 24, release commit Oct 25, docs update Oct 27, announced Oct 28)"}],"claims":["Lab claim: sustains production runs of more than 10 hours and more than 2,000 turns.","Lab claim: preliminary results show good visual composition and motion choreography in motion design."],"sources":[{"kind":"lab","title":"SenseTime announcement on X","url":"https://x.com/SenseTime_AI/status/2115445835068748044","date":"2026-10-28"},{"kind":"repo","title":"SenseNova-6.8-Code2Video on Hugging Face","url":"https://huggingface.co/sensenova/SenseNova-6.8-Code2Video"},{"kind":"repo","title":"OpenSenseNova/SenseNova-6.8-Code2Video on GitHub (skill and prompts)","url":"https://github.com/OpenSenseNova/SenseNova-6.8-Code2Video"}],"peer":{"slug":"qwen3-8-27b","label":"its base model, Qwen3.8 27B"},"firstBenchmark":null},"organization":{"id":"sensetime","name":"SenseTime","slug":"sensetime","country":null,"url":null,"color":"#A39E8F","mark":"SE"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 28, 2026; no independent results yet.","lead":"As of Nov 3, 2026, SenseNova 6.8 Code2Video 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":[]}