This is a model used to explore your imagination with prompts that output very nice images relative to the prompt in real life. The image I started with was a 1600 ISO image of the moon behind clouds around 2:00 AM. What this means because I did not edit the image, some of the noise carries into the image, but it does make it look more realistic. I then made a 32 image set out of that image and made a LoRA. I then merged that LoRA with the standard SDXL Base Model. The file is quite large, but contains a large amount of data for this type of image generation. Landscape means landscape, but the Base Model is very tightly confined to the original image used.
Settings: Trial and error is best, but these settings should be a good place to start
SDXL_Nature_Landscape : Model
sd_xl_refiner_1.0_0.9vae : Refiner / Refiner Switch@Trial/Error is best
None: LoRA
Image : PNG
Steps : 30
Guidance Scale : 6.8
Image Sharpness : 0 to .68
Description
This is a model used to explore your imagination with prompts that output very nice images relative to the prompt in real life. The image I started with was a 1600 ISO image of the moon behind clouds around 2:00 AM. What this means because I did not edit the image, some of the noise carries into the image, but it does make it look more realistic. I then made a 32 image set out of that image and made a LoRA. I then merged that LoRA with the standard SDXL Base Model. The file is quite large, but contains a large amount of data for this type of image generation. Landscape means landscape, but the Base Model is very tightly confined to the original image used.
Settings: Trial and error is best, but these settings should be a good place to start
SDXL_Nature_Landscape : Model
sd_xl_refiner_1.0_0.9vae : Refiner / Refiner Switch@Trial/Error is best
None: LoRA
Image : PNG
Steps : 30
Guidance Scale : 6.8
Image Sharpness : 0 to .68
Comments (2)
I like this model
so far all i get is clouds and a building and its blurred. Over and over. Maybe an object and those things. I'm thinking more than one picture is needed for this experiment.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.