ADDED PROMPTS TO MOST OF THE PREVIEW IMAGES. THESE PROMPTS DO NOT INCLUDE THE FINAL STAGE WHICH IS IMG2IMG UPSCALE USING MULTI-DIFFUSION. UNFORTUNATELY CIVITAI HAS NO WAY OF SHOWING THIS STEP. I WILL FIND THE BEST METHOD OF POSTING THE NECESSARY INFORMATION TO YOU ALL. UNTIL THEN I CAN AT LEAST PROVIDE A LINK TO THE EXTENSION AND MY SETTINGS
TILED VAE Encoder Tile Size: 1024 Decoder Tile Size: 128 Fast Encoder: Checked Fast Decoder: Checked Encoder Color Fix: Checked
The prompt can help elevate or hide elements of your image.
Example prompt: "Apocalyptic Art Style, Pseudorealism, Gigapixel Image, splash art style, Beauty Filter, cinematic lighting, digital illustration, digital art, 2.5d, masterpiece, best quality, highres, HDR, unreal engine 5"
Digital Illustration, Digital Art, Masterpiece, Best Quality and Highresare standard just to make sure it knows to keep them in the digital style. Apocalyptic Art Style(without weights) to continue the theme. Splash Art Style: Same as above Pseudorealism+ 2.5D They act synergistic to nudge the image from pure line art into a bit more of a hybrid, making the art less painted and more digital. Beauty Filter, Cinematic Lighting, HDR: With beauty filter being the main addition to the prompt to add "beauty" to the subject with improved lighting using cinematic lighting and HDR. Gigapixel Image, Unreal Engine 5: Gigapixel Image (while I'm unsure if it works) is a plugin and software used in high end upscaling, hypothetically by prompting it you add a bit of the style or flavor that the finished product of a Gigapixel Image receives. Giving it a 'high end' feel to it. While Unreal Engine 5 will help bring it all together into a common aesthetic, which won't dominate but influence the upscaled image.
These are my thoughts and motivations to why I included those in one upscale prompt.
Improved background quality and versatility
Made them more prominent and less saturated or clouded
(assuming you prompt it right, as always)
Made the model more versatile overall in the styles supported
Sci-Fi now more broadly able to be generated, rough and gritty or crystal clear
Dark Fantasy maintains same quality
As does Gothic Fantasy
Dieselpunk and Cyberpunk improved, especially combinations of the two
Combat, including actual engagement and (though admittedly harder to prompt for) killing blows mostly of the anime style.
Even some sci-fi though I'm unsure of how much
Holding weapons expanded
My model in 2.1 was quite capable of holding weapons, this has been further improved upon in 3.0 to also include some firearms but they do have the biggest issue with those
Sometimes hands in general, or holding weapons will bug out and you'll suffer the standard spazzed out hands. Spaghetti fingers, lacking a finger or having an extra, but this shouldn't happen too often unless your prompt and negative prompt is lacking.
Tested and confirmed to be working very well with Multi diffusion
All example images are upscaled with Tiled Diffusion and Tiled Vae, which are part of Multi Diffusion extension
Aside from fixing bigger problems with the version, this is the last Dark Gemini. If I release another, it will be under another name and a new upload.
Follow me if you'd like to be updated
For more information on how to prompt, I refer you to the guides for both 2.0 and 2.1 as they both function well enough. The model accepts both simple and complex and very long prompts.
Most example images will come with a prompt for how the original was made but not how it was upscaled. Which includes 1 of several quality prompts and a denoise of 0.3-0.4. Then upscaled with Tiled Diffusion and Tiled VAE. Below are the settings I sometimes use on my 3070 ti 8GB GPU, which is the only one I ever had while making or testing my models.
ADDED PROMPTS TO MOST OF THE PREVIEW IMAGES. THESE PROMPTS DO NOT INCLUDE THE FINAL STAGE WHICH IS IMG2IMG UPSCALE USING MULTI-DIFFUSION. UNFORTUNATELY CIVITAI HAS NO WAY OF SHOWING THIS STEP. I WILL FIND THE BEST METHOD OF POSTING THE NECESSARY INFORMATION TO YOU ALL. UNTIL THEN I CAN AT LEAST PROVIDE A LINK TO THE EXTENSION AND MY SETTINGS
https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111
Sampler: DPM++ 2S a
Steps: 30
CFG scale: 7
Denoising strength: 0.4
TILED DIFFUSION
Tiled Diffusion upscaler: R-ESRGAN 4x+ Anime6B
Tiled Diffusion scale factor: 2.5
Tiled Diffusion:
Method': 'MultiDiffusion'
Latent tile width': 96
Latent tile height': 96
'Overlap': 32,
'Tile batch size': 1
TILED VAE
Encoder Tile Size: 1024
Decoder Tile Size: 128
Fast Encoder: Checked
Fast Decoder: Checked
Encoder Color Fix: Checked
The prompt can help elevate or hide elements of your image.
Example prompt: "Apocalyptic Art Style, Pseudorealism, Gigapixel Image, splash art style, Beauty Filter, cinematic lighting, digital illustration, digital art, 2.5d, masterpiece, best quality, highres, HDR, unreal engine 5"
Digital Illustration, Digital Art, Masterpiece, Best Quality and Highres are standard just to make sure it knows to keep them in the digital style.
Apocalyptic Art Style (without weights) to continue the theme.
Splash Art Style: Same as above
Pseudorealism + 2.5D They act synergistic to nudge the image from pure line art into a bit more of a hybrid, making the art less painted and more digital.
Beauty Filter, Cinematic Lighting, HDR: With beauty filter being the main addition to the prompt to add "beauty" to the subject with improved lighting using cinematic lighting and HDR.
Gigapixel Image, Unreal Engine 5: Gigapixel Image (while I'm unsure if it works) is a plugin and software used in high end upscaling, hypothetically by prompting it you add a bit of the style or flavor that the finished product of a Gigapixel Image receives. Giving it a 'high end' feel to it. While Unreal Engine 5 will help bring it all together into a common aesthetic, which won't dominate but influence the upscaled image.
These are my thoughts and motivations to why I included those in one upscale prompt.
Improved background quality and versatility
Made them more prominent and less saturated or clouded
(assuming you prompt it right, as always)
Made the model more versatile overall in the styles supported
Sci-Fi now more broadly able to be generated, rough and gritty or crystal clear
Dark Fantasy maintains same quality
As does Gothic Fantasy
Dieselpunk and Cyberpunk improved, especially combinations of the two
Combat, including actual engagement and (though admittedly harder to prompt for) killing blows mostly of the anime style.
Even some sci-fi though I'm unsure of how much
Holding weapons expanded
My model in 2.1 was quite capable of holding weapons, this has been further improved upon in 3.0 to also include some firearms but they do have the biggest issue with those
Sometimes hands in general, or holding weapons will bug out and you'll suffer the standard spazzed out hands. Spaghetti fingers, lacking a finger or having an extra, but this shouldn't happen too often unless your prompt and negative prompt is lacking.
Tested and confirmed to be working very well with Multi diffusion
All example images are upscaled with Tiled Diffusion and Tiled Vae, which are part of Multi Diffusion extension
Aside from fixing bigger problems with the version, this is the last Dark Gemini. If I release another, it will be under another name and a new upload.
Follow me if you'd like to be updated
For more information on how to prompt, I refer you to the guides for both 2.0 and 2.1 as they both function well enough. The model accepts both simple and complex and very long prompts.
Most example images will come with a prompt for how the original was made but not how it was upscaled. Which includes 1 of several quality prompts and a denoise of 0.3-0.4. Then upscaled with Tiled Diffusion and Tiled VAE. Below are the settings I sometimes use on my 3070 ti 8GB GPU, which is the only one I ever had while making or testing my models.
Tiled Diffusion; https://cdn.discordapp.com/attachments/1037809583281942632/1097930020892184726/image.png
Tiled VAE: https://cdn.discordapp.com/attachments/1037809583281942632/1097930322798202890/image.png