DreamShaper V7
欢迎使用DreamShaper V7 - 一个为写实风格好者设计的latent diffusion模型。这个模型旨在仅用少数几个提示词就能生成高质量、高细节的写实风格。与其他风格的Stable Diffusion模型一样，它还支持danbooru标签来生成图像。
NOTES
Version 7 improves lora support, NSFW and realism. If you're interested in "absolute" realism, try AbsoluteReality.
Version 6 adds more lora support and more style in general. It should also be better at generating directly at 1024 height (but be careful with it). 6.x are all improvements.
Version 5 is the best at photorealism and has noise offset.
Version 4 is much better with anime (can do them with no LoRA) and booru tags. IT might be harder to control if you're used to caption style, so you might still want to use version 3.31.
V4 is also better with eyes at lower resolutions. Overall is like a "fix" of V3 and shouldn't be too much different.
Results of version 3.32 "clip fix" will vary from the examples (produced on 3.31, which I personally prefer).
I get no money from any generative service, but you can buy me a coffee.
You should use 3.32 for mixing, so the clip error doesn't spread.
Inpainting models are only for inpaint and outpaint, not txt2img or mixing.
Original v1 description: After a lot of tests I'm finally releasing my mix model. This started as a model to make good portraits that do not look like cg or photos with heavy filters, but more like actual paintings. The result is a model capable of doing portraits like I wanted, but also great backgrounds and anime-style characters. Below you can find some suggestions, including LoRA networks to make anime style images.
I hope you'll enjoy it as much as I do.
Official HF repository: https://huggingface.co/Lykon/DreamShaper
Suggested settings:
- I had CLIP skip 2 on some pics (all of them for version 4)
- I had ENSD: 31337 for basically all of them
- All of them had highres.fix or img2img at higher resolution.
- I don't use restore faces, as it washes out the painting effect
- Versions >4 require no LoRA for anime style. For version 3 I suggest to use one of these LoRA networks at 0.35 weight: -- https://civitai.com/models/4219 (the girls with glasses or if it says wanostyle) -- https://huggingface.co/closertodeath/dpepmkmp/blob/main/last.pt (if it says mksk style) -- https://civitai.com/models/4982/anime-screencap-style-lora (not used for any example but works great).
NOTE: if you find that the prompts below look "familiar" it's because I've taken them from other reviews and models here, to basically compare my model to other examples. Credits to the original authors. Thanks for the benchmark.
使用方式
from modelscope.utils.constant import Tasks
from modelscope.pipelines import pipeline
import cv2
pipe = pipeline(task=Tasks.text_to_image_synthesis,
model='lionetest/dreamshaper-v7.0',
model_revision='v7.0')
prompt = 'c4d, pvc, 1girl, with a cat,cute, <lora:C4D:0.6>,pov, selfie, masterpiece, best quality,<lora:ghibli_style_offset:1.0><lora:ghibli_style_offset:1.0>'
output = pipe({'text': prompt})
cv2.imwrite('result.png', output['output_imgs'][0])
License
这个模型是开放的，所有人都可以使用，CreativeML OpenRAIL-M许可证进一步规定了权利和使用。CreativeML OpenRAIL许可证规定了：
- 你不能使用这个模型来故意产生或分享非法或有害的输出或内容。
- 作者对你产生的输出结果没有任何权利，你可以自由使用它们，并对它们的使用负责，但不得违反许可证中的规定。
- 你可以重新发布模型权重，并在商业上作为一项服务使用该模型。如果你这样做，请注意你必须包括与许可证中相同的使用限制，并将CreativeML OpenRAIL-M的副本分享给你的所有用户（请完全仔细阅读许可证）。 请在这里阅读完整的许可证。
评论