Edit Model for V8
By Steven Van ·
Hey everyone! Today we’re gonna start letting everyone test our first V8.2 image edit model!
Midjourney has opened testing of its first V8.2 image edit model to everyone. The model supports:
- Editing images with text instructions
- Generating images from up to four reference images at once, replacing the omni-reference tool
- Inpainting specific areas of an image or outpainting to expand the canvas
- Personalization, moodboards and style references, though moodboards and srefs may need extra prompt direction in this version
The edit model can be reached by dragging an image into the prompt bar under "attach to prompt", clicking edit in the lightbox, using the edit tab to upload an image, or typing --edit url... on Discord. Midjourney has updated the interface on both midjourney.com and alpha.midjourney.com, and says alpha will keep changing rapidly as it tests new interface designs for the model. Feedback on edits that don't work can be left via the sad face emoji in the lightbox, or by sharing the job ID or URL in the announcement's linked Discord channels, #ideas-and-features and #edit-showcase.
