sketch style for img2img (pruned update) – sketch_style_v1
| Run Model | 使用GRAVITI Diffus 关于GRAVITI Diffus |
| Model Name | sketch style for img2img (pruned update) |
| Model Type | Checkpoint |
| Base Model | SD 1.5 |
| Version Name | sketch_style_v1 |
| File Name | sketchStyleForImg2img_sketchStyleV1.ckpt |
| SHA256 | f481f5e732 |
| NSFW | False |
| Trigger Words | |
| Tags | anime, character, style, illustration |
| Metadata | fp = fp16 size = full format = PickleTensor |
| Size | 3.97 GB |
| Version Description |
事实上，这个模型经过几次迭代，但仍旧是它的效果最好 In fact, this model has gone through several iterations, but this is still the best one 适用于手绘风格生成以及照片转手绘风格 Suitable for hand-drawn style generation and photo-to-hand-drawn style 能够较好展现大多数tag It can display most tags well 某些角度的手部效果不错 Hands at certain angles work well |
| Source | https://civitai.com/models/12628 |
| Author | duxin |
适用于手绘风格生成以及照片转手绘风格
Suitable for hand-drawn style generation and photo-to-hand-drawn style
修剪后的模型更新
pruned model update
(感谢 @juvesatriani 的帮助)
(Thanks for @juvesatriani‘s help)
以下是V2.5与V2和V1的对比（V1,V2,V2.5）：
Here’s how V2.5 compares to V2 and V1 (V1,V2,V2.5):
以下是三个版本图生图的对比：
Here’s a comparison of the img2img between these Versions:
模型最开始是用来生成二次元正太的（φ(゜▽゜*)♪），但是意外
发现对于图生图特别友好，尤其是照片之类的，下面是两个示例：
(The model was orignally used to generate anime boys((′д｀ )…彡…彡,but it was unexpected have goods results about img 2 img,here is some example)
If there is a translation error, please let me know in the comments
（tags：{{masterpiece}},best quality,illustration,1 male kid,prince,rose,floating short hair,yellow hair,long yellow scarf,green clothes,rose,closeup,chibi）
针对图生图的示例如下：
There are some example of img2img
（以下所有真人照片均出自this-person-does-not-exist）
（All of the following live photos are from this-person-does-not-exist）
推荐的图生图参数：steps：30，cfg：11，denoising strength：0.52，使用clip进行反推文本
Recommended img2img parameter: steps:30，cfg:11，denoising strength:0.52,Use clip to reverse text
相关文章
