wan2.7-r2v-2026-06-12 · wan · video
Wan 2.7 reference-to-video model supports multimodal input (image/video/audio) to generate videos that keep character identity and voice consistent, for single-character or multi-character scenes.
Multi-subject reference (image+video+voice); single multi-grid (storyboard) reference; voice reference.
Character-consistent video, digital humans, multi-character interaction, storyboard creation.
Reference images+videos ≤5; 2-10s with video reference, 2-15s without; asynchronous; result URL valid 24h.
Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.
export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="wan2.7-r2v-2026-06-12"
claude