Corona Style LyCORIS [SD-1.5]

This is a SD V1-5 version LoRA/LyCORIS, with a trigger word of C0r0n4 eclipse.

This model was trained using 151 publicly available photograph and scientific images of partial and total solar eclipses.

This model is a SD V1.5 LoRA trained using Kohya_ss (https://github.com/kohya-ss/sd-scripts) webui (https://github.com/bmaltais/kohya_ss). Sample images were rendered using A1111 (https://github.com/AUTOMATIC1111/stable-diffusion-webui).

Sample Prompt:

RAW photograph of a (city skyline at night),with a (C0r0n4 eclipse:0.9) (rising high in the sky above),surrounded by bright solar corona,HDR,(wide angle shot),sharp focus,(highly detailed),(8k wallpaper),intricately detailed,highres,absurdres,hyper realistic,8K UHD DSLR,IMAX,extremely intricate,4k textures,cinematic look),hyperdetailed,<lora:C0r0n4_SD1-5:0.7>,

If you are pleased with the models provided, I would be grateful for your support with a 👍 Like, 🚶 Follow, or ❤ Review. I greatly appreciate your comments, feedback, and images which helps me continue to improve my model workflow, testing, and image generation.

I am also extremely grateful for tips ☕ if you appreciate my work, (https://buymeacoffee.com/Signalytix), as it helps significantly to offset my costs and effort, allowing me to devote more time to research, create, contribute, and share my work with the community. Suggestions posted to my tips page (https://buymeacoffee.com/Signalytix) garner my utmost attention for new models. I currently focus on development of LoRAs and embeddings for SDXL and V1.5.

------------------------------------------------------

Model Card:

Name: C0r0n4_SD1-5:0.9

Version: 1-SDXL

Description: Corona Eclipse, a LoRA/LyCORIS model of Solar Eclipses

Trigger Words: C0r0n4 eclipse

Data Set: 151 images (768x768)

Epochs: 2

Steps: 386

Batches: 4

Repeats: 25

Optimizer: DAdaptAdam

Base Model: runwayml/stable-diffusion-v1-5

------------------------------------------------------

ARTIFICIAL HUMANS ASSOCIATION (AHA) CERTIFICATION:

No WAIFUS were harmed, exploited, or compromised in the training of this model or creation of images.