HeyGen: HeyGen just launched HeyGen MCP. It lets you make HeyGen videos right inside other AI tools.
You can use it in tools like Claude Web, Claude Code, Gemini CLI and Cursor... no need to jump between apps.
Just connect your HeyGen account using OAuth. After that you make videos using the same plan you already have.
So your AI agent can create videos for you... right from the tool you’re working in.
FLORA: Image Editor is now live:
composite, inpaint, outpaint, resize, split into layers. It’s a complete editing environment inside your generative workflow.
OpenArt: Vellum - the new tool improves the skin so it looks more real, removing that plastic style skin and bringing back the small things real photos show... pores, skin detail, depth and natural light.
Comfy Cloud: Two big updates just landed for the ComfyUI ecosystem.
1. App Mode. It puts the node graph power behind a simple interface. So people turn big messy workflows into small custom apps you can run with a few clicks... much easier to use.
2. ComfyHub. A new place where people can find, run and share workflows or apps fast using a link. You open a URL and try it right away.
MuAPI: You can now make very long AI videos with Seedance 2.0 Extend. The tool lets you keep adding new parts to the same video again and again. The parts connect in a smooth way and keep the same flow.
+ A free Seedance 2.0 watermark remover on MuAPI.
InVideo AI: Invideo shares a tool for quickly making music videos. Just upload your track and the system handles the rest - no need to write prompts or edit clips. Pick a preset and press create. The video comes together in under a minute.
Dreamina AI: Javi Lopez on X says Seedance 2.0 is getting heavily nerfed.
For example just typing “gun” may block it.
He says the user experience inside Dreamina keeps getting worse day by day.
He jokes that by the time it fully launches people might only be able to create rainbows unicorns and hearts... nothing else.
Kling AI: Artificial Analysis reports that Kling 3.0 1080p Pro now ranks first in Text to Video. It leads both the With Audio and Without Audio boards in the Artificial Analysis Video Arena. It moves ahead of Grok Imagine, Runway Gen 4.5 and Veo 3.1.
For Image to Video the results look a bit different. Kling 3.0 1080p Pro ranks fourth on the With Audio board and sixth on the No Audio list. It follows Grok Imagine and PixVerse V5.6 in those spots.
