Runway shipped Agent Skills on July 2, one-command actions inside its marketing agent that build an ad campaign, create a commercial, or localize your ads from a single prompt, live across all plans.
claude-real-video is a local CLI that pulls scene-change frames, dedupes repeats, and transcribes audio so Claude, ChatGPT, or Gemini can actually watch a video, not just read its transcript.
Apple Creator Studio's June 2026 update threads AI captions, edit detection, auto mask, and image generation through Final Cut Pro, Logic Pro, and Pixelmator Pro.
ByteDance Seedance 2.0 Mini and native 4K video are now selectable inside ComfyUI's existing Seedance nodes, with ready-made templates for text, frame, and reference workflows.
HappyHorse 1.1 lands in ComfyUI as a partner node that generates video with synchronized dialogue and sound effects in a single render pass.
ComfyUI shipped v0.26.0 with native nodes for Kling V3-Turbo, Luma Rays 3.2, Krea2, Qwen3-VL, Boogu-Image, SCAIL-2, HappyHorse 1.1, and a new advanced 3D loader, all in one release.
How animator Xindi Zhang built her Oscar-shortlisted thesis film in ComfyUI using style transfer, custom LoRAs trained on her own footage, and AI morphing.
Run ByteDance's Bernini-R video and image editing model entirely on your own GPU in ComfyUI. A step-by-step GGUF workflow for local, reference-guided edits with no cloud render fees.
LTX Director 2.0 turns Lightricks LTX 2.3 into a full timeline-based video editor inside ComfyUI, adding IC-LoRA, Retake Mode, and audio inpainting.
ComfyUI shipped v0.25.0 and v0.25.1 in three days, adding Kling V3-Turbo, Depth Anything 3, Tripo3D, and native 3D preview nodes.
Runway's Aleph 2.0 video model is now available inside Figma Weave, letting designers and editors direct clips up to 30 seconds frame by frame from Weave's node-based canvas.
xAI pushed Grok Imagine Video 1.5 to wide release on June 17, 2026, topping the image-to-video leaderboard with native audio at about $4.20 per minute, roughly 86 percent below Sora 2.
OpenAI is retiring Sora, turning the AI video race into a two-horse contest. Here is how Kling 3 and Runway compare on price, resolution, audio, and multi-shot control, plus a safe migration path off Sora.
AI video generation costs anywhere from half a cent to over forty cents per second in 2026. This guide compares Veo, Runway, Kling, Luma and Avataar Varya on real cost per second and shows where the savings are.
Luma added Skills to Luma Agents, a way to save a creative workflow once and re-run it on new footage or images for consistent results.
Meta is rolling out generative photo and video editing tools inside the Facebook app, letting you swap clothing, hair, and accessories.
The best AI tools for video editors in 2026 pair real timeline editing with AI: DaVinci Resolve Studio leads, with Premiere Pro, Runway, Descript, and Topaz Video AI close behind. Here is how the top tools compare on features, pricing, and who each is for.
Take a song from a blank prompt to a finished, beat-synced music video in an afternoon using three tools: Suno for the track, Runway Gen-4 for the visuals, and CapCut for the edit.
Descript shipped inline tone tags for ElevenLabs V3 speakers and a connector for Claude and ChatGPT on June 11, 2026, pushing further into directable AI editing.
Avataar launched Varya, an AI video model at roughly $0.005 per second, about 20x cheaper than Veo, Runway, Kling, or Luma, with an open-weight release planned.
DaVinci Resolve 21 adds a Photo page so you can edit RAW stills and grade video in one free app. Here is the full hybrid shooter workflow.
Shengshu AI released minWM on May 28, an Apache 2.0 framework that converts open video models like Wan2.1 and HunyuanVideo into real-time interactive world models with camera control.
A solo developer shipped Snipforge on May 27, 2026: 28 AI-powered video tools that run entirely in your browser, requiring no installation and no account to start.
PARE achieves 52% parameter reduction on Wan2.1-14B with just 0.6 points drop on VBench, using spatial-temporal aware pruning and content-adaptive routing. Combined with step distillation, total speedup reaches 50x.