Ideogram launches v4.5 with strong natural-language image editing
gen_ericai · x · 2026-10-01
Ideogram has launched version 4.5, and early hands-on testing shows its natural-language image editing is notably strong. In the demo, the author assembled a new image from two previous generations in 4.5, then edited it via a plain-language prompt with impressive results.
Related event: Ideogram 4.5 Debuts with Precise Editing, Open Weights Planned(4 posts)→
More from Multimodal
- ElevenReader rolls out Eleven v4: more expressive voices and language support jumps from 32 to 90+ — lukeharries · 2026-10-01
- Creatify's Model Playground locks first/last frames, mixes product, person, scene, audio references — testingcatalog · 2026-10-01
- Creatify post-trains MiniMax H3 into ad video model Boreal-H3, lifting brief success from 28% to 50% — testingcatalog · 2026-10-01
- Runway hosts AI Summit, demos running policy built on its world models — c_valenzuelab · 2026-10-01
- HeyGen Launches Its First General-Purpose Video Model at $0.01/s, Claiming to Beat Veo 3.1 — HeyGen · 2026-10-01
- ComfyUI launches Comfy API: deploy workflow JSONs as autoscaling endpoints — PurzBeats · 2026-10-01