CivArchive
    NONE-768-v2 - v2
    Preview 1
    Preview 2
    Preview 3
    Preview 4
    Preview 5

    Description

    Business Cooperation/Open AI Community  QQ: 592532681  QQ Group: 820145842

    This model is supplemented with nearly 40,000 pieces of my 1.5PLUS materials and trained for over five hundred hours

    Trained to 768 short edge output, significantly improved clarity and overall content integrity

    Tags with small main subjects can be reduced to 512 short edge output

    Model advantages are my old three: composition, photography, lighting

    Recommended parameters: 2m/2m SDE/3m SDE sampler

                                   steps 20-30

                                   CFG: 7

    Negative Tags: Required (worst quality: 1.5), bad anatomy, (wrong anatomy)

                      Optional (do not fill out when dealing with fantasy and cg) CG, CGI, illustration, cartoon

                      Default probability film if you do not want

    Required Plugin:AfterDetailer face editing plugin, do not use facial repair!!!


    Great existing high-definition restoration can be used 1.5-2 times

                      Enlargement algorithm recommendation: 4x-UltraSharp 2 times redesign range 0.2-0.4

                                            or 8x-NMKD 2 times redesign range 0.2-0.4

                                               AfterDetailer face editing plugin, do not use facial repair!!!


      In the rapid development of current AI visual technology, we have established a research and development team with AI as the core driving force, aiming to help break through the diversity of art and creativity and liberate production bottleneck as our vision -NiuNeng Technology

          The main members include former Huawei Nanjing Research Institute Senior Software Engineering EngineerLIONEL, former Nanjing Algorithm Research Institute Senior Algorithm EngineerShaolin Knight, MoYou Artificial Human series stable model developer Central Academy of Fine Arts ArtistMoYou, and several other top industry personnel from the None series model author LIBLIBAI training lecturerNONE.

          In the future, we will delve into the research and development of AI vision, focusing on practical scenario applications, upholding the original intention of enabling everyone to enjoy a new ecosystem of AI technology, and forging ahead!



    FAQ

    Details

    Downloads
    105
    Platform
    ShakkerAI
    Platform Status
    Available
    Created
    2/1/2024
    Updated
    9/6/2024
    Deleted
    -

    Files