Higgsfield steals the internet, Pixverse has a record on Frames, and Lovart is open

All the news from the AI world for creatives

New AI-powered tools are quietly reshaping how we create videos, shop, code, and how we invent characters in seconds.

1️⃣ Higgsfield steals the internet

2️⃣ Pixverse has a record: Up to 7 Keyframe for your scene

3️⃣ Lovart, the Design Agent is open

4️⃣ Quick news you may have missed

5️⃣ Video AI of the Week

Let’s dive in.

Higgsfield steals the internet

Higgsfield has now released Steal. This feature allows you to recreate any picture from anywhere on the web. This is the process:

• Install the new Higgsfield Browser Extension.

• Hover any image on the web, hit Recreate.

• Same pose, lighting, outfit: but YOU are the star.

---

Pixverse has a record: Up to 7 Keyframe for your scene

Pixverse has introduced Multi-Keyframe Generation. You can upload up to 7 images and control the duration of transitions and frame-to-frame changes. Adjust camera angles, create smooth transitions, or add dynamic effects.

---

Lovart, the Design Agent is open

Lovart, an application with Design Agent capabilities, is now open, ending its beta phase. It promises to be provide design powered by AI. Without templates or the need for perfect prompts.

---

Quick news you may have missed

• Midjourney has released three new features for video:

  1) You can now create looping videos
  2) You can now make videos with a specific start and end images
  3) Video generation is now available on Discord. Here is how video works on Discord:

  • To make videos click the "Animate" buttons under upscales.,

  • If you have remix mode enabled, you can provide a prompt for the video.,

  • To animate an image from outside of Midjourney, enter the image url at the start of the prompt and use the --video arg,

  • To get a higher-quality .mp4, click one of the virtual upscale buttons on a video,

  • Videos can be extended. Turn on remix mode to change the prompt when extending,

  • To make a looping video, use --loop in the prompt,

  • To set an end frame, use --end image_url

• ChatGPT agent has been now fully rolled out to all Plus, Pro, and Team users. Agent is an unified agentic system combining Operator’s action-taking remote browser, deep research’s web synthesis, and ChatGPT’s conversational strengths.

• Kling’s Elements for Image to Video generation has received a major upgrade in subject consistency, dynamics, prompt adherence, and visual rendering quality.

---

Video of the Week

NeuralViz has released Cop Files VI. If you haven't watched Cop Files Part IV & V, I definitely suggest doing that first. Written, directed, edited, performed, and sound designed by the same creator.

---

Thanks for reading. Enjoy your Sunday, touch grass, and have a nice coffee.