ARTificialJourney-1.0 768X768

This is an AI model trained on ~100 hand picked 768X768 images targeted to get the best close up portrait pictures, as well as amazing looking landscapes. This model does not handle full-body portraits well due to being trained on more close up images, but it will be improved in the next update of this model. Please use the keywords "artificial-journey style" before or after the prompt. Also be sure to add more detailed text to the prompt to get the best results. Resolutions 1024x768px, 768x1024px, and 768x768 work best for this model.

.safetensors file was generated using the new sd-webui-model-converter.

Examples (As is images, no upsclaing or face improvements were used)

Have fun generating!

CKPT & Safetensors Download

Download ARTificialJourneyV1-768px.ckpt) (2.9GB)

Download ARTificialJourneyV1-768px.safetensors) (2.9GB)

? Diffusers

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion Pipeline .

from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
import torch

prompt = (
"artificial-journey style portrait of male dark magician, d & d, dark eyeliner, intricate, elegant, highly detailed, digital painting, artstation, concept art, matte, sharp focus, illustration")

model_id = "Kaludi/ARTificialJourney-v1.0-768"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

image = pipe(prompt, num_inference_steps=30).images[0]

image.save("./result.jpg")

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies: