%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Join Now
Artificial intelligence-generated image field has seen another major upgrade. AI painting giant Midjourney recently officially announced the launch of its first V8.2 image editing model for public testing, targeting a broad user base. The core of this update lies in completely breaking away from the previous single-mode of generating images solely based on text. By deeply integrating advanced features such as instruction fine-tuning, multi-image reference, and localized re-painting, it offers creators a more precise and controllable professional visual creation experience.
In terms of core features, the V8.2 image editing model mainly supports four technical characteristics: first, powerful instruction editing capabilities, allowing users to directly modify existing images through text instructions; second, a brand-new multi-image reference generation mechanism that can completely replace the previous panoramic reference (omni-reference), and supports up to four images being merged simultaneously in one go; third, localized re-painting (inpainting) and canvas extension (outpainting) functions for specific areas, making image detail adjustments and size extensions effortless; finally, full compatibility with personalized settings, mood boards, and style references (srefs). However, the official also reminds users that using mood boards or style references in this version may achieve better artistic effects when combined with additional prompt guidance.
To ensure a smooth experience across different workflows, Midjourney has adapted various convenient usage methods for this model. Users can directly drag an image into the prompt input box and select the "Attach to Prompt" function, or click the "Edit" button at the bottom right corner of the previewlightbox, or upload an image through the "Edit" tab in the left navigation bar. It also supports calling the model directly by entering commands in a Discord channel.
In terms of product ecosystem and interface iteration, the official has also updated the Midjourney official website and the alpha.midjourney.com testing site. Since this is still in the early stage of functional testing, the test version interface will rapidly iterate due to frequent experimental optimizations. The official also admits that the new model may still encounter some unexpected challenges when dealing with complex edge cases, so they highly need the help and feedback from the community. If users encounter situations that do not meet expectations during the creative process, they can provide feedback to the development team via the emoji symbols on the right side of the lightbox or by providing a task ID, or directly share their ideas in the official communication channel's creative and feature suggestion area.
Details: https://updates.midjourney.com/edit-model-for-v8/