{"id":23750,"date":"2026-03-25T11:29:04","date_gmt":"2026-03-25T18:29:04","guid":{"rendered":"https:\/\/jnack.com\/blog\/?p=23750"},"modified":"2026-03-25T20:11:19","modified_gmt":"2026-03-26T03:11:19","slug":"i-loveart-to-move-it-move-it","status":"publish","type":"post","link":"https:\/\/jnack.com\/blog\/2026\/03\/25\/i-loveart-to-move-it-move-it\/","title":{"rendered":"I Love(art) to move it, move it…"},"content":{"rendered":"\n

I’ve long quoted James Ratliff, the super sharp designer behind Adobe’s Project Graph (who’s recently decamped to Figma), in nicely phrasing how the process of generating & refining ideas generally starts broad\/declarative (searching, prompting) and moves towards fine-grained methods (selecting, moving, etc.):<\/p>\n\n\n\n

\"\"<\/a><\/figure>\n\n\n\n

I see an increasing number of tool & model creators mixing modalities\u2014even in the Gemini Super Bowl ad featuring a mom & daughter drawing a simple circle to show where they’d like to add a dog bed.<\/p>\n\n\n\n

I’m eager to check out Lovart’s<\/a> take on the possibilities, especially for animation:<\/p>\n\n\n

\n

\u26a1\ufe0f New on Lovart: Move Object<\/p>\n

\u2192 Select any object with rectangular or lasso tool
\u2192 Move it wherever you want
\u2192 Prompt optional modifications
\u2192 One clean, consistent image<\/p>\n

No masks. No layers. No re-roll. pic.twitter.com\/Sw800icnsu<\/a><\/p>\n

\u2014 LovartAI (@lovart_ai) March 25, 2026<\/a><\/p>\n<\/blockquote>\n