oldPhoto_v1.0.safetensors

144 MB · SafeTensor

Requer assinatura

<fake-documentary>

If you enjoy my work, please give me a "like" rating; it means a lot to me! I don't speak English, but I wrote the explanation very carefully. It won't take more than two minutes to read. The following translation is from ChatGPT. 《fake documentary》 At first, I just wanted to create a Lora that could generate old photos. Gradually, I found that old photos have a unique sense of reality and history, so I tried to add some interesting elements to it. This is why I trained dozens of versions until this version emerged, as you can see now, it can create some huge content that does not exist in reality, but still looks real! Of course, it can also create a lot of interesting content, which depends on your imagination. Now I can't wait to see your works! 一开始我只是想创造一个能够生成老照片的lora，渐渐的，我发现老照片具有一种独特的真实感和历史感，所以我尝试为它增加一些有趣的元素，这也就是为什么我训练了数十个版本，直到这个版本的出现，正如你现在所见，它可以创造一些巨大的现实中不存在的内容，但看起来依旧真实！当然，它也可以创作很多有趣的内容，这取决于你的想象力，现在我等不及要看到你们的作品啦！ How to do it ? Firstly, during the collection of materials, I found that the color of old photos can be divided into several types, which are: Sepia Old Photo / Yellowed Old Photo / Grayscale Old Photo / Old Photo. As long as you choose any one of them as a trigger word, it will present a picture with different colors (note, do not mix and use them). 首先，在收集资料的时候，我发现老照片的成色可以分成几种，它们分别是：sepia Old Photo / Yellowed Old Photo / grayscale Old Photo / Old Photo，只要你选用任意一种作为触发词，都会呈现出不同成色的画面（注意，不可混用） Secondly, as time goes by, old photos are subject to varying degrees of damage, which I have categorized as: damaged / Light Leaks / Scratches / dust. These can serve as trigger words, and of course, you can include all of them in your prompt. However, to be honest, I did not train it in this way, so the final effect may differ from what you might imagine. 其次，随着时光的流逝，老照片会受到不同程度的破坏，我将它分类为：damaged / Light Leaks / Scratches / dust，作为触发词，你当然可以将它们全部加到提示词中，但坦白讲，我并没有这样训练它，所以最终呈现的效果，可能和你的想象会有些不同。 Finally, as a simulation of old photos, the classification of the era seems to be important as well (though this is not mandatory). Photography was invented by the French in 1839, and taking this as the starting point, I have set up multiple time points as the third category of trigger words. They are as follows: Early 19th Century / in 19th Century / Early 20th Century / 1960s / 1970s / 1980s / 1990s. From the examples above, you can see that as the era gets closer to the present, the colors in the images also become more vivid, which is exactly what I want. 最后，作为模拟老照片，年代划分似乎也很重要（这不是必须的）摄影术是由法国玉1839年发明，以此为起点，我为它设置了多个时间点作为第三类触发词，它们分别是：Early 19th Century / in 19th Century / Early 20th Century / 1960s / 1970s / 1980s / 1990s 从上面的示例中你可以看出，随着年代越来越近，图像的颜色也会越来越鲜活，这就是我想要的。 Alright! Now we have three sets of trigger words that you can combine in any way to test the effect you want to achieve. For example, "sepia old photo," "damaged," "early 19th century," is a good combination. 好啦！现在我们有三组触发词，你可以任意组合它们，来测试你想实现的效果，比如：sepia old photo，damaged，early 19th century，就是一组不错的组合。 How to do it Sampler：DPM++ 2M Karras Steps：39 CFG Scale：6 lora weight：0.3~0.9 Hires.fix：4x_NMKD-Siax_200k Steps：9 Denoising：0.39 Additional notes In addition to these amazing features, you will also find that it still works very well even without using prompt words. It just has a slightly different effect, to be precise, it enhances the film texture of the image, and you don't have to worry about overexposure or being too dark. 除了这些神奇的功能，你还会发现，即使不使用提示词，它仍然能很好的工作，只是功效会有些许不同，准确的说是为画面增强胶片质感，不用担心曝光过度或者黑成一团 I hope you have fun！Peace！

SHA256

8C461B4D282CC7A62C2DCF86BBBFB3AB0F2DE1D979664F136633B42BBA0F2AA1

ID de modelo ModelTrends.ai

#2913

Sampler

DPM++ 2M Karras

Passos

39

Guidance

6

Seed

1690376470

Tamanho

520x960

Clip skip

2

Sampler

DPM++ 2M Karras

Passos

39

Guidance

6

Seed

1275871187

Tamanho

520x960

Clip skip

2

Sampler

DPM++ 2M Karras

Passos

39

Guidance

6

Seed

1015044639

Tamanho

520x960

Clip skip

2

Sampler

DPM++ 2M Karras

Passos

39

Guidance

6

Seed

4174894037

Tamanho

520x960

Clip skip

2

Sampler

Euler a

Passos

25

Guidance

3.5

Seed

383090442

Tamanho

512x768

Clip skip

2

Peso usado

1

Sampler

DPM++ 2M Karras

Passos

39

Guidance

6

Seed

4231351955

Tamanho

520x960

Clip skip

2

Sampler

DPM++ 2M Karras

Passos

30

Guidance

6

Seed

4083680403

Tamanho

640x960

Clip skip

2