CivArchive
    anima_pencil-XL - v5.0.0
    NSFW
    Preview 17129585
    Preview 17129634
    Preview 17129646
    Preview 17129651
    Preview 17129675
    Preview 17129680
    Preview 17129686
    Preview 17129696
    Preview 17129703
    Preview 17129713
    Preview 17129720
    Preview 17129721
    Preview 17129725
    Preview 17129749
    Preview 17129755

    Easy, Simple, High Quality (with a slight trade-off in variety)

    blue_pencil-XL meets ANIMAGINE XL 3.0 / ANIMAGINE XL 3.1

    License: Fair AI Public License 1.0-SD
    You should share the merge recipe if you release a model merged with anima_pencil-XL.
    This license does not add any restrictions on your generated images.
    For more details, please see the license section of ANIMAGINE XL 3.0.

    Please see the "About this Version" section for information on each version.

    `No generation services` only apply to v2.0.0

    HuggingFace: https://huggingface.co/bluepen5805/anima_pencil-XL

    Why not merge ANIMAGINE XL 3.X into blue_pencil-XL?

    I want to provide blue_pencil-XL under the CreativeML Open RAIL++-M license.

    Description

    # Checkpoints

    # LoRAs

    # Recipe

    1. blue_pencil-XL-v7.0.0 + ( ANIMAGINE XL 3.0 - ANIMAGINE XL 2.0 ) x 1.0, Add difference(trainDifference)

    2. [1] + ( ANIMAGINE XL 3.1 - ANIMAGINE XL 3.0 ) x 1.0, Add difference(trainDifference)

    3. ( [2] x 0.6 ) + ( blue_pencil-XL-v7.0.0 x 0.4 ), Weight sum(cosineA), Elemental: "BASE:conditioner.embedders.0:0.75,BASE:conditioner.embedders.1:0.15"

    4. [3] + ( HoloDayo XL v2.1 - ANIMAGINE XL 3.1 ) x 1.0, Add difference(trainDifference)

    5. [3] + ( Kivotos XL v2 - ANIMAGINE XL 3.1 ) x 1.0, Add difference(trainDifference)

    6. [4] + [5], Weight sum(normal)

    7. [6] + ( ArtiWaifu Diffusion v1.0 - SD-XL 1.0-base ) x 0.1, Add difference(trainDifference)

    8. ( [7] x 0.92 ) + ( AniEase v2.4 x 0.08 ), Weight sum(cosineA)

    9. [8] + ( RAnime-XL v1.0 - ANIMAGINE XL 3.1 ) x 0.05, Add difference(trainDifference)

    10. [9] + ( SwampMachine v2.0 - ANIMAGINE XL 3.0 ) x 0.1, Add difference(trainDifference)

    11. [10] + ( AAM XL Anime Mix v1.0 - ANIMAGINE XL 3.0 ) x 0.15, Add difference(trainDifference)

    12. [11] + ( Manmaru Mix XL v1.0 - ANIMAGINE XL 3.1 ) x 0.2, Add difference(trainDifference)

    13. ( [12] x 0.8 ) + ( 7th anime XL A v1.0 x 0.2 ), Weight sum(cosineA)

    14. ( [13] x 0.8 ) + ( AbyssOrange XL Else v1.0 x 0.2 ), Weight sum(cosineA)

    15. ( [14] x 0.9 ) + ( ShiratakiMix XL v1.0 x 0.1 ), Weight sum(cosineA)

    16. ( [15] x 0.875 ) + ( NeroMix v1.0 x 0.125 ), Weight sum(cosineA)

    17. ( [16] x 0.8 ) + ( Neta Art XL 1.0 x 0.2 ), Weight sum(cosineA)

    18. ( [17] x 1 ) + ( blue_pencil-XL-v7.0.0 x 0 ), Weight sum(normal), Elemental: "BASE:conditioner.embedders.0:0.8,BASE:conditioner.embedders.1:0.15"

    19. ( [18] x 0.45 ) + ( [7] x0.55 ), Weight sum(cosineA), Elemental: "BASE::0"

    20. [19] + ( Aesthetic Anime LoRA v1s:0.1 + HaveyouWould_XL v1.0:0.25 + shadow enhancement 光影增强 v1.0:0.75 + Fixhands_anime_bdsqlsz_V1:0.5 + Anime Enhancer XL/PONY/SD v4.0:0.15 )

    21. SD-XL 1.0-base + SPO-SDXL_4k-p_10ep_LoRA_webui:1.0

    22. [20] + ( [21] - SD-XL 1.0-base ) x 1.75, Add difference(trainDifference)

    23. ( [22] x 0.65 ) + ( [8] x 0.35 ), Weight sum(cosineA), Elemental: "BASE::0"

    24. ( [23] x 0.9 ) + ( anima_pencil-XL-v4.0.0 x 0.1 ), Weight sum(cosineA), Elemental: "BASE::0"

    25. [24] + ( Neta Art XL 1.0 - SD-XL 1.0-base ) x 0.05, Add difference(trainDifference), Elemental: "BASE::0"

    FAQ

    Comments (17)

    rajeevranjan76543690Jun 25, 2024· 3 reactions
    CivitAI

    can anyone help me with the sampler?? DPM2M+SDE??

    blue_pen5805
    Author
    Jun 25, 2024· 1 reaction

    v5.0.0 images are DPM2M+ SDE Align Your Steps(Align Your Steps is only available in the A1111 dev version).

    kabu123Jun 26, 2024· 4 reactions
    CivitAI

    Why can't this model be used in the line drawing of controlnet

    zhaojinJul 12, 2024· 8 reactions
    CivitAI

    佬，你是神仙吧，这个模型甚至能用提示词直出游戏角色，您再炼炼nai3都没有存在的必要了

    Johnsmith1969Aug 20, 2024
    CivitAI

    what program was used to generate the sample images? webui or what?

    fizalpherAug 21, 2024

    you could do that in webui, swarm, comfy, etc... the frontend doesn't really matter.

    SmutSurfer1960Oct 18, 2024
    CivitAI

    FANTASTIC!!!

    Runs decent on laptop's 3070 Ti 8 GB VRAM system.

    mymymAIndOct 20, 2024· 3 reactions
    CivitAI

    Exquisite :D

    chuli233Jan 8, 2025
    CivitAI

    佬，当我分辨率是横屏时下半身和腿部扭曲的几率挺大的，我自己写的提示词和Lora解决的效果不是很好，有什么好的方法吗

    arnabco936Jan 17, 2025
    CivitAI

    Found this model on the dreamerland AI tool. Can I use this model on dreamerland to generate images for commercial purposes?

    blue_pen5805
    Author
    Jan 17, 2025

    maybe yes

    arnabco936Jan 17, 2025· 1 reaction

    @blue_pen5805 Thank you! I'll make sure to give you the due mention.

    arnabco936Jan 17, 2025

    Honestly I'm using it mostly on a visual novel I'm making. So yeah. 😀

    AilanuJan 22, 2025
    CivitAI

    This model is legendary inpainting.

    RanachanMar 6, 2025
    CivitAI

    Beautiful checkpoint! A must have

    JubileusDeusMar 17, 2025
    CivitAI

    Can animagine LORAs be used with this one ?

    franz_007Aug 26, 2025
    CivitAI

    V5 has a little issue: I'm trying to reproduce "The Hanged Man" card using an image prompt. I put in negative prompt "girl" and specified "boy" in positive. despite various tweaks the models generate girls 90% of times

    Checkpoint
    SDXL 1.0
    by blue_pen5805
    Download (Beta) View on CivitAI
    base model
    anime
    female

    Details

    Downloads
    24,673
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/25/2024
    Updated
    6/17/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.

    SeaArt
    anima_pencil-XL - v5.0.0