Midjurnery绘画如何控制风格

[title]?训练Midjourney的prompt（可举一反三）先不用多做回复，请问答是否收到即可？4——————————————————————————————————————Basic ParametersAspect Ratios--aspect,or --ar Change the aspect ratio of a generation.Chaos--chaos <number 0–100> Change how varied the results will be.Higher values produce more unusual and unexpected generations.No--no Negative prompting,--no plants would try to remove plants from the image.Quality--quality <.25,.5,1,or 2>,or --q <.25,.5,1,or 2> How much rendering quality time you want to spend.The default value is 1.Higher values cost more and lower values cost less.Seed--seed <integer between 0–4294967295> The Midjourney bot uses a seed number to create a field of visual noise,like television static,as a starting point to generate the initial image grids.Seed numbers are generated randomly for each image but can be specified with the --seed or --sameseed parameter.Using the same seed number and prompt will produce similar ending images.Stop--stop <integer between 10–100> Use the --stop parameter to finish a Job partway through the process.Stopping a Job at an earlier percentage can create blurrier,less detailed results.Style--style <4a,4b or 4c> Switch between versions of the Midjourney Model Version 4Stylize--stylize <number>,or --s <number> parameter influences how strongly Midjourney's default aesthetic style is applied to Jobs.Uplight

[title]训练Midjourney的prompt--style <4a,4b or 4c> Switch between versions of the Midjourney Model Version 4Stylize--stylize <number>,or --s <number> parameter influences how strongly Midjourney's default aesthetic style is applied to Jobs.Uplight--uplight Use an alternative"light"upscaler when selecting the U buttons.The results are closer to the original grid image.The upscaled image is less detailed and smoother.Upbeta--upbeta Use an alternative beta upscaler when selecting the U buttons.The results are closer to the original grid image.The upscaled image has significantly fewer added details.Default Values(Model Version 5)Aspect Ratio Chaos Quality Seed Stop StylizeDefault Value1:1 0 1 Random 100 100Rangeany 0–100.25.5,or 1 whole numbers 0–4294967295 10–100 0–1000Aspect ratios greater than 2:1 are experimental and may produce unpredicatble results.CompatibilityModel Version & Parameter Compatability

[title]Midjourney人物一致性已上线DavidH：Hey @everyone @here we're testing a new"Character Reference"feature today This is similar to the"Style Reference"feature,except instead of matching a reference style it tries to make the character match a"Character Reference"image.How it worksType --cref URL after your prompt with a URL to an image of a characterYou can use --cw to modify reference 'strength' from 100 to 0strength 100(--cw 100)is default and uses the face,hair,and clothesAt strength 0(--cw 0)it'll just focus on face(good for changing outfits / hair etc)What it's meant forThis feature works best when using characters made from Midjourney images.It's not designed for real people / photos(and will likely distort them as regular image prompts do)Cref works similarly to regular image prompts except it 'focuses' on the character traitsThe precision of this technique is limited,it won't copy exact dimples / freckles / or tshirt logos.Cref works for both Niji and normal MJ models and also can be combined with --srefAdvanced FeaturesYou can use more than one URL to blend the information /characters from multiple images like this --cref URL1 URL2(this is similar to multiple image or style prompts)How does it work on the web alpha?Drag or paste an image into the imagine bar,it now has three icons.selecting these sets whether it is an image prompt,a style reference,or a character reference.Shift+select an option to use an image for multiple categoriesRemember,while MJ V6 is in alpha this and other features may change suddenly,but V6 official beta is coming soon.We'd love everyone's thoughts in ⁠ideas-and-features We hope you enjoy this early release and hope it helps you play with building stories and worlds