SenseNova releases Code2Video, an Apache-2.0 multimodal model built on Qwen3.5
solyarisoftware · x · 2026-11-02
SenseNova has released SenseNova-6.8-Code2Video on Hugging Face, a multimodal model that turns code and images into video descriptions, built on Qwen3.5 and aimed at code-video tasks.
The model card lists it as Image-Text-to-Text, supports English and Chinese, and is released under the Apache-2.0 license, with tags including video-generation and agent.
More from Multimodal
- An uncanny blue-skinned three-eyed AI-generated video frame is going viral — SydSteyerhart · 2026-11-02
- Qwen Image 2.1 Realtime upgraded with v1.5 two-step distill LoRA — linoy_tsaban · 2026-11-02
- AI-generated Ferrari driver in an Iron Man helmet is a style-fusion showcase — Delahuntagram · 2026-11-02
- Novice shares a MiniMax H3 fight-scene workflow: 8-step turbo plus Topaz to 60fps — Beginning_Tip300 · 2026-11-02
- Phonic launches Phonic-1 speech-to-speech model alongside $27.5M Series A — amos_gyamfi · 2026-11-02
- Rebuilding 4 ComfyUI workflows into a zero-dependency app with DLSS 5 and VRAM streaming — MCP1964 · 2026-11-02