童话绘本/fairy tale style(国内独家)

LORA
Original


Updated:

822

大家好,我是chosen鲷,这次带来的是童话绘本lora。

训练这个模型的初衷是想要一个像儿童画一般充满天马行空想象力的模型,所以找了很多绘本风格的图训练了这个。

这个lora可以作为风格挂件使用,但是权重别太大,0.7顶天了,作为挂件的话0.40.5什么的就可以了。触发词:fairytalestyle

推荐的tag:

(masterpiece:1.2), best quality,PIXIV,fairy tale style
这里写你想要的内容
<lora:fairy tale style-000016:0.7>
Negative prompt: EasyNegative, badhandsv5-neg,Subtitles,word,
Steps: 32, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 2741718913, Size: 512x768, Model hash: c3ff8d00a6, Model: chosen irises bake vae, Denoising strength: 0.6, Clip skip: 2, ADetailer model: mediapipe_face_full, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.6.1.post0, Hires upscale: 2, Hires steps: 12, Hires upscaler: Latent, Lora hashes: "fairy tale style-000016: 1a111cc2d185", Version: v1.4.1

大模型我推荐用我的chosen irisse(就是下方推荐里第一个),其他的模型我尝试了感觉味道都差点,没那个鲜亮的感觉,但是推荐用扁平画风的二次元插画模型.

The following content is from Google Translate

Hello everyone, I am Chosen Roach, and this time I bring you Lora, the Fairy Tale style Lora.

The original intention of training this model was to create a model that embodies the wild imagination seen in children's drawings. Therefore, I collected many images with a picture book style to train this model.

Lora can be used as a decorative piece with a specific style, but please don't set the weight too high. 0.7 is the maximum value, and for decorative purposes, 0.4 or 0.5 would be sufficient. Trigger phrase: fairy tale style

Recommended tags: (masterpiece:1.2), best quality, PIXIV, fairy tale style

Please write down the content you want.

<lora:fairy tale style-000016:0.7>

Negative prompt: EasyNegative, badhandsv5-neg, Subtitles, word

Steps: 32, Sampler: DPM++ SDE Karras, CFG scale: 7, Seed: 2741718913, Size: 512x768, Model hash: c3ff8d00a6, Model: Chosen Irises Bake VAE, Denoising strength: 0.6, Clip skip: 2, ADetailer model: mediapipe_face_full, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer version: 23.6.1.post0, Hires upscale: 2, Hires steps: 12, Hires upscaler: Latent Lora hashes: "fairy tale style-000016: 1a111cc2d185" Version: v1.4.1

For the large model, I recommend using my Chosen Irises (the first one in the recommended models below). I have tried other models, but they lacked that vibrant feeling. However, I suggest using a two-dimensional illustration model with a flat art style.

Thank you all for downloading and using my models. If you like them, please feel free to follow me. My Bilibili and Pixiv IDs are both Chosen Roach. You are welcome to check out my channels at https://space.bilibili.com/3867754?spm_id_from=333.1007.0.0 and https://www.pixiv.net/users/40911695. Thank you.

Version Detail

SD 1.5

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.