CivArchive
    Kontext Figure Maker By Aldniki - v1.0
    NSFW
    Preview 95797746
    Preview 95797873
    Preview 95795603
    Preview 95795644

    You can use the online workflow below. If the results are good, you can then try setting it up and running it locally.

    👉 Click Here For Online WorkFlow

    As a fan benefit, you’ll receive 1,000 points upon registration, plus 100 points for daily logins. Enjoy a smooth experience with an RTX 4090 and 48GB of VRAM.

    Model Description

    This LoRA is designed to convert 2D anime-style images into realistic 3D figures.
    Best results are achieved with full-body character images, ensuring the model captures complete proportions and poses.

    • Sampler: Euler

    • CFG: 2.0

    • LoRA Weight: 0.95

    • Steps: 25

    • Recommended to use high-resolution upscale: 1.5× scale. Denoising can be set between 0.4–0.7. Beta scheduler is recommended, with 12 steps, CFG 1.0.

    reveal the person's entire body, the character has a tall body like a super model, maintain the character's pose and extract the main character and turn it into a realistic 3d figure. on a round clear plastic base, place the figure version of the photo. I'd like the PVC material to be clearly represented. It would be even better if the background is indoors.

    Alternative Prompt (Result quality not guaranteed)

    This model can also achieve effects similar to Nano Banana, but the results are very unstable. Generating images like the ones above requires some luck, but those who want to try it can give it a shot.

    show the full body and maintain the pose, the character has tall body and long legs, turn it into a realistic 3d figure. Behind it, there should be a Model packaging box with the extracted colored character from this photo printed on it. There should also be a computer, with the content on the computer screen showing the Blender grey color modeling process of the figurine. In front of the computer screen, on a round clear plastic base, place the figure version of the photo. I'd like the PVC material to be clearly represented. It would be even better if the background is indoors.

    (Text in red can be modified or removed on your choice)

    Use Cases

    ✅ Anime characters → Realistic 3D figure style
    ✅ Custom figurine design for games/anime characters
    ✅ Q-version or scaled figurine exploration
    ✅ Combine with other LoRAs for creative results

    模型介绍

    这个 LoRA 可以将 二次元风格图片转化为真实的 3D 手办效果
    注意: 原图最好是完整的人物 全身照,这样能达到最佳效果。

    推荐设置

    • 采样器: Euler

    • CFG: 2.0

    • LoRA 权重: 0.95

    • 步数: 25

    • 推荐使用高清放大: 1.5倍. 降噪 0.4–0.7. Beta 调度器, 12步, CFG 1.0。

    推荐提示词

    reveal the person's entire body, the character has a tall body like a super model, maintain the character's pose and extract the main character and turn it into a realistic 3d figure. on a round clear plastic base, place the figure version of the photo. I'd like the PVC material to be clearly represented. It would be even better if the background is indoors.

    其他可用提示词 (不保证结果质量)

    这个模型也可以做到像是nano banana那样的效果,但是生成效果很不稳定,生成类似上面的图片需要运气,想尝试的人可以尝试

    show the full body and maintain the pose, the character has tall body and long legs, turn it into a realistic 3d figure. Behind it, there should be a Model packaging box with the extracted colored character from this photo printed on it. There should also be a computer, with the content on the computer screen showing the Blender grey color modeling process of the figurine. In front of the computer screen, on a round clear plastic base, place the figure version of the photo. I'd like the PVC material to be clearly represented. It would be even better if the background is indoors.

    (标红文字可以修改或删除)

    使用场景

    ✅ 二次元角色 → 现实手办风格
    ✅ 游戏/动漫角色定制 3D 化
    ✅ Q版/比例手办效果探索
    ✅ 与其他 LoRA 搭配增强创作

    Description

    FAQ

    Comments (8)

    xcross48Aug 22, 2025· 3 reactions
    CivitAI

    看起来很棒啊

    martinliu1104501Aug 22, 2025· 1 reaction
    CivitAI

    Is this model used for https://m.youtube.com/shorts/EDEhmu6iTkY ???

    aldniki217
    Author
    Aug 22, 2025

    Most likely the video used this model. Although some other paid models can also achieve the figure effect, the images in this video handle many details in a way that’s very similar to my LoRA. The video is quite good, and this LoRA has achieved its goal

    MikeflowerAug 23, 2025· 1 reaction
    CivitAI

    😍 👍🏻

    krigetaAug 23, 2025· 1 reaction
    CivitAI

    Hey, can you train a Lora for anime image change the pose by depth, openpose and canny?

    like kinda controlnet but you know pose transfer and can do multiple character too.

    aldniki217
    Author
    Aug 23, 2025

    There are some other creators working on this concept, but honestly it's quite challenging. I'll probably work on this later.

    armani55Aug 24, 2025

    I think it can be done by putting in an open posed stick figure and applying LoRA since it is kontext.

    WithoutOrdinaryNov 21, 2025
    CivitAI

    Workflow is is invalid with the current version of ComfyUI and attempting to load it breaks the frontend.

    LORA
    Flux.1 Kontext

    Details

    Downloads
    2,548
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/22/2025
    Updated
    5/13/2026
    Deleted
    -

    Available On (1 platform)

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