AI Video2026
Enables Claude to “watch” videos by extracting timestamped frames plus captions/transcripts and feeding them to Claude for grounded Q&A. Key features: native captions first, Whisper fallback, frame deduplication, and multiple detail modes (transcript/efficient/balanced/token-burner). Useful for summarizing, debugging, and extracting moments.
AI Video2026
Cross-platform native video editor with hardware-accelerated processing and frame-accurate multi-track timeline; core editor is open-source and free while optional Pro AI features (natural-language editing, auto-captions, smart reframing) are paid.
AI Dataset2026
Large-scale synthetic video dataset of 236,937 1080p clips (≈5,841 hours) of digital humans with per-frame metric depth and camera parameters — built as a controllable supplement for world-model pretraining, camera-motion generalization, and geometry-aware physical-AI research.
AI Model2026
Image-to-video (I2V) diffusion model merge tuned for prompt-conditioned motion and evolution. Uses layer-scaled weight merges (not straight averaging) with BF16 and FP8 checkpoint options; prompt engineering is required for predictable motion and audio. Avoid large distilled Loras for best results.
AI Dataset2026
Structured, downloadable JSONL dataset of Seedance 2.0 video-generation prompts with matching MP4 previews and cover images; includes English/Chinese texts and standardized metadata (duration, resolution, safety) and is released under CC BY 4.0 for reuse.
AI Dataset2026
Provides 1.3 billion platform-specific video URLs extracted from CommonCrawl along with crawl metadata (no media included), serving as the source corpus for the LAION-BVD multimodal video dataset; distributed on Hugging Face in Parquet format.
AI Model2026
Generates uncensored videos from text and images using an LTX 2.3–based diffusion model with native t2v and i2v support; ships with a prompt enhancer and developer-focused gguf/bf16 dev releases for local experimentation.
AI Dataset2026
Provides 55 million scene-level video clips (each with captions, language labels, and timestamps) extracted from an 80M-video, 10-million-hour raw pool to support multimodal pre-training across video, audio, and frames. Access is gated for academic/non-commercial research.
AI Dataset2026
Open egocentric multimodal dataset for embodied AI and robot learning captured on commodity iPhone Pro: ~200 hours and ~10M RGB frames with LiDAR depth, ARKit 6‑DoF poses, IMU, two‑hand MANO mocap, room meshes, and hierarchical action captions.
AI Dataset2026
Provides tick-aligned Counter-Strike 2 player POV video clips with per-tick inputs and world-state sidecars — near-lossless 1280×720@32fps video, per-player stereo audio, and parquet indexes for event/kill/round filtering; suited for RL, video classification and clip mining.
AI Model2026
Converts video inputs into text outputs — supports captioning, temporal grounding, and video-text-to-text queries using a Qwen-3.5-2B finetuned multimodal backbone. Suited for prototyping video understanding and caption-generation pipelines.
AI Model2026
Delivers image and video generation, editing, and understanding inside a single 3B-parameter multimodal model trained from scratch with a multi-task recipe. Notable for strong unified benchmarks at 3B scale; inference requires large GPU memory (≈40GB+ VRAM).