Midjourney V8.2 launches image editing model with instruction-based edits and 4-image reference
LudovicCreator · x · 2026-08-28
Midjourney has released its first V8.2 image editing model, introducing several key features:
- Instruction-based editing: Modify images directly via text prompts.
- Multi-image reference generation: Replaces omni-reference, supporting up to 4 reference images simultaneously.
- Inpainting & Outpainting: Supports changing specific areas or expanding the canvas.
The author conducted an initial test, noting that personalization and moodboards work best with some extra prompt direction in this version.
More from Multimodal
- Krea launches new 'Three' model for image generation — chrisfirst · 2026-08-28
- Midjourney v8.2 Editing Features Tested: Removal & Repaint — LudovicCreator · 2026-08-28
- Krea AI launches new Krea Three model at NYC event — chrisfirst · 2026-08-28
- Google DeepMind Releases ORBIT++ Benchmark for SfM in 360° Video — taiyasaki · 2026-08-28
- MiniMax H3 pure text-to-video test with a full shot-by-shot prompt — BitterAd8431 · 2026-08-28
- Peking Univ & Kling Unveil MAVIN to Solve Multi-Shot Video Narrative Challenges — 机器之心 · 2026-08-28