You can use my model directly at : Tensort.Art | Mage.Space
_____
Units can contact me if they want to release for commercial or exclusive use ( Facebook | Zalo | Mail )
_____
If you find it useful, please vote 5 stars and post an image to help me, it's really important, I thank you all very much.
_____
In addition, I have some LoRa trained for SDVN8, you can refer to it on my TensordArt page.
_____
📖 Checkpoint Info
Info : This is a model that I am very passionate about and selected after a series of different tests and methods. It leans heavily on 2D elements, anime, illustrator, art style. I train a lot of data in many different genres to achieve the best efficiency. In addition to the base version, (designed to balance different styles), I also have special versions that are trained with additional data that favors a specific style for users to choose from. I have made some comparisons with other versions, you can refer to it for more information
____
You can refer to some of the indicators below to achieve the best image quality :
Steps : > 30
CFG : 9-10
Size : 768x1152 px ( or 800x1200px ), 1024x1024
You can also use hiresfix ( hiresfix is not really good at SDXL, if you use it please consider denoising streng 0.2-0.3 ) or After Detailer
Sampling : Euler a
📝 Quality Prompt :
Base quality prompt :
(masterpiece,best quality)Key :
ghibli, anime style, horror style, sticker design, portrait art style, illustrator...📝 Negative Prompt :
low quality, illustration, 3d, 2d, painting, cartoons, sketch_____
Also you can test those prompt tags quickly with my model here : Tensor.art
I have written a colab site that integrates all tools for you to use stablediffusion without configuring your computer, you can refer to : Colab SDVN
I have provided an album with more than 2000 original photos with full prompt, you can refer to understand how to use SDXL : SDVN-SDXLPrompt Kit
In addition, some of my models are available on the Mage.space platform, you can refer to: SDVN Mage
_____
On top of that, SDXL is only in its early stages, I may have many shortcomings. I hope you can give me suggestions for corrections in the next updates. If you find it useful, please vote 5 stars and post an image to help me, it's really important, I thank you all very much
_____
👨🏻💻 Creator : stablediffusion.vn
📢 Discord : Discord SDVN
📢 Facebook : Group SDVN
☕️ Donate me : Bank | Buymeacoffee
Description
A little tip, please type in a keyword that is the name of your favorite Ghibli movie, it's very useful
FAQ
Comments (11)
What's the difference between Base and 'yourname'? Did you forget to give the second one a title?
I'm going to go ahead and guess that it's stylistically similar to the art found in the acclaimed anime movie "Your Name," a brilliant film from Makoto Shinkai. A lot of the light and cloud effects look very similar to the film.
@hollaman Ah that makes sense. I wasn't aware of that movie, thank you.
Those are two different versions, the yourname version is based on the style of the anime of the same name and is continued from the base version ^^
Can update version artsyle?
Sure, I'm developing the next versions of this model
Hmm without money
Hmm Hiroyuki Kitazume art
I notice that you keep concepts like "illustration", "sketch" and "painting" in the recommended negative prompt, even though they seem to sometimes match the output's category. Is there any specific reason behind this recommendation?
I found that there are prompts in your showcase pictures that use "sketch" in both the positive and negative, which was believed to cause deteriorated result by many of the community, but in fact the generated image is of quite high quality. I wonder if you could share any insight about this? Thanks.
please SD1.5 model
It's insanely good for horror stuff.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.