One image turned into a seamless 4-part carousel with Midjourney and ChatGPT
umesh_ai · x · 2026-09-15
A creator shares a workflow that turns a single image into a seamless 4-part social carousel by combining Midjourney and ChatGPT, with before/after visuals showing how the image is split and extended while staying visually coherent.
More from Multimodal
- VLMs can think with value maps: latent visual tokens in CoT yield 20% accuracy gain — burny_tech · 2026-09-15
- H3 Acceleration Arena adds 3 new video models for speed-quality evaluation — multimodalart · 2026-09-15
- Chinese Creators Turn Dismissed "AI Slop" Video Into a Profession — HeyZoyaKhan · 2026-09-15
- Grok Imagine images meet MiniMax H2 video in an AI creation combo — creatoroff · 2026-09-15
- Matthias Niessner: an RTX 5070 renders billions of triangles per second — CSProfKGD · 2026-09-15
- Solo dev open-sources a free local ElevenLabs replacement with voice cloning in 646 languages — nikola_mr64990 · 2026-09-15