You can use my model directly at : Tensort.Art | Mage.Space
_____
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
_____
📖 Checkpoint Info
Info : This is a training model based on the best quality photos created from SDVN3-RealArt model. With the desire to bring the beauty of SD1.5 to SDXL model. I added a bit of real life and skin detailing to improve facial detail. Currently I have two versions Beautyface and Slimface.Detailface version is an upgrade of Beautyface, it creates more skin details and creates better realism than the beautyface version. With the Beautyface version - the model face will have more diverse angular lines. In contrast, the Slimface version will have a slimmer and easier-to-see model face, suitable for Asian faces.
_____
You can refer to some of the indicators below to achieve the best image quality :
Steps : > 50
CFG : 9-10
Size : 768x1162 px ( or 800x1200px )
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 or DPM ++ SDE Karass
📝 Quality Prompt :
Base quality prompt :
(masterpiece,best quality, ultra realistic,32k,RAW photo,detail skin, 8k uhd, dslr,high quality, film grain:1.5),📝 Negative Prompt :
(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), tooth, open mouth,💡 Concept reference:
Portrait Lady Real :
(masterpiece,best quality, ultra realistic,32k,RAW photo,detail skin, 8k uhd, dslr,high quality, film grain:1.5),
{short hair | long hair}, __*/haircolor__ hair,lady, brown eyes, __*/colors__ __*/Wear/*__, freckles,
(__*/colors__ gradient background, simple background:1.3)_____
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
This is an upgraded version of the beautyface version, in this version, I continue to upgrade more skin details to create a more realistic image quality. I tried to improve the body proportions, but it affected the realistic quality and model face a bit, so I didn't do that. If you want to do photos with more standard body proportions. Try my SDVN7
FAQ
Comments (10)
This model looks promising. I spent far too much time on SD 1.5 and seeing all these airbrush unrealistic SDXL models just seems meh but this looks good OP! I hope A111 get's SDXL controlnet soon. Will be huge.
Thank you, I'm working on a more complete update for this model
Is there something I need to install previously to run XL checkpoints? All XL checkpoints I try to load, fail to load and the UI defaults to another checkpoint.
I don't think my gpu is the problem. I've reinstalled, rebooted, and updated. All the usual fixes.
are you using comfy or automatic1111?
@raccoon1111 Hi! I was using A1111, the problem was the following: I always used git pull to update. I thought that would update the version of the UI but it didn't. So I finally downloaded the 1.6 version and I was able to load the XL models!
@Nyoon glad that you were able to solve the problem
显存低于6G就跑不了吧？
Hi, can you help me how to fix faces when generate a group of people? it does a perfect job when creating a single person.
Thanks
Hello - sdvn6Realxl_detailface just doesn’t work here. I’ve used it just doesn’t work. I see it hopeful 'rendering' in 'Display Progress Images' at InvokeAi and in the End every time it turns all black (no fun ). I run it with LinuxMint. Maybe others were successful with locally run versions but at least for me running it on here, it gave me this 'black pic' errors every time. I am happy to change my review when/if this works so please reach out in the future if this has been fixed and if it has and I can actually create images I will give it a new review but in its current state, it’s just unusable. wish you good luck
in my terminal no exceptions occur
<TOTAL GRAPH EXECUTION TIME: 18.827s .....
I am not a programmer in my opinion in this last process it turns the pic to black
[2024-03-18 20:59:22,149]::[uvicorn.access]::INFO --> 127.0.0.1:49362 - "GET /api/v1/images/i/1d4cb11b-4284-449e-b943-ac9a7f60d00c.png/metadata HTTP/1.1" 200 />
During the process the image is visible but once it is finished the image remains black, solution?
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.