HomeAI News
Midjourney V5 Official Announcement
3

Midjourney V5 Official Announcement

Russell
Russell
March 30th, 2023
View OriginalTranslated by Google

Hello everyone, we will try to alpha test our version of the V5 algorithm. To turn it on, type --v 5 at the prompt or select "v5" from /settings

What's new in the V5 base model?

  • Wider range of styles, more responsive to cues
  • Higher image quality (2x resolution increase), improved dynamic range
  • More detailed images. The details are more likely to be correct. Unwanted text is not required.
  • Improve performance with image hints
  • Support --tile argument for seamless tiling (experimental)
  • Support for aspect ratios greater than 2:1 --ar aspect ratio (experimental)
  • Support - iw for weighing image hints vs text hints

V5 Styles and Tips

  • Today's test is basically the "Pro" mode of the model.
  • It's much more 'unbiased' than v3 and v4, and is tuned to provide a variety of outputs and be very responsive to your input.
  • The tradeoff here is that it might be harder to use. Short prompts may not work well. You should try to write long, clear text about what you want (ie: "film photo with dramatic lighting effects").
  • Please chat with each other in prompt-chat to learn how to use v5.
  • We want to have a "friendly" default style before switching it to default. When that happens, we'll still allow you to turn it off and go back to "raw" mode similar to today.



Please note

  • This is an alpha test and things will change. Do not rely on the exact model being available in the future. As we push V5 toward general release, it will be significantly revised.
  • Now there is no V5 upsampler, the default resolution is the same as upscaled V4. If you click to enlarge, only the image itself is given immediately.



community standards

  • This model can generate more realistic images than anything we have published before.
  • We've increased the number of moderators, improved moderator tools, and are enforcing our Community Standards with greater rigor and rigor. Don't be an asshole or create controversial images.

More information about V5

V5 is our second model trained on an AI supercluster and has been running for 5 months. It uses significantly different neural architectures and new aesthetic techniques. V5 is not the final step, but hopefully all of you feel the power of something deep and incomprehensible in the collective human imagination.

Please use these incredibly powerful abilities with joy, wonder, responsibility and respect

have fun! ❤️

(original) Hi everyone we're going to try alpha-testing a version of our V5 algorithms. To turn it on type --v 5 after your prompt or select "V5" from /settings

What's new with the V5 base model?

  • Much wider stylistic range and more responsive to prompting
  • Much higher image quality (2x resolution increase) improved dynamic range
  • More detailed images. Details more likely to be correct. Less unwanted text.
  • Improved performance with image prompting
  • Supports --tile argument for seamless tiling (experimental)
  • Supports --ar aspect ratios greater than 2:1 (experimental)
  • Supports --iw for weighing image prompts versus text prompts

Style and prompting for V5

  • Today's test is basically a 'pro' mode of the model.
  • It's MUCH more 'unopinionated' than v3 and v4, and is tuned to provide a wide diversity of outputs and to be very responsive to your inputs.
  • The tradeoff here is that it may be harder to use. Short prompts may not work as well. You should try to write longer, more explicit text about what you want (ie: “cinematic photo with dramatic lighting”)
  • Please chat with each other in prompt-chat to figure out how to use v5.
  • We hope to have a 'friendly' default styling for v5 before we switch it to default. When this happens we will still let you turn it off and get back to something like this 'raw' mode today.

Please note

  • This is an alpha test and things will change. DO NOT rely on this exact model being available in the future. It will be significantly modified as we take V5 to full release.
  • Right now there is no V5 upsampler, the default resolution of V5 is the same as upscaled V4. If you click upscale it will just instantly give you that one image by itself.

Community Standards:

  • This model can generate much more realistic imagery than anything we've released before.
  • We've increased the number of moderators, improved moderation tooling, and will be enforcing our community standards with increased strictness and rigor. Don't be a jerk or create images to cause drama.

More about V5: V5 is our second model trained on our AI supercluster and has been in the works for 5 months. It uses significantly different neural architectures and new aesthetic techniques. V5 isn't the final step, but we hope you all feel the progression of something de ep and unfathomable in the power of our collective human imagination.

Please use these incredible powers with joy, and wonder, responsibility and respect Have fun! ❤️

Comments

no dataCoffee time! Feel free to comment