img2img Experiments with StableDiffusion | Lora | Hypernet

This series of experiments show a common use of differently trained AI models in combination „filtering“ a raw input photo via img2img. Therefore we need to distiguish between (free downloadable!) base models like Stable Diffusion Checkpoint Files (ckpt) we can image as base engine and additional models (lora or hypernetwork) that might manipulate the basic outcome.

CyberRealistic 1.3
DreamShaper 4.0

Ghibli Style Lora
Figma Anime Figures
MJV4 Hypernetwork

cyberrealistic / dreamshaper / ghibli style

cyberrealistic & ghibli
dreamshaper & ghibli

cyberrealistic / dreamshaper / figma

dreamshaper & figma
cyberrealistic & figma

cyberrealistic / dreamshaper / no Lora

cyberrealistic / no lora
dreamshaper / no lora

(masterpiece, best quality, absurdres:1.2), photo of a highly detailed (figma) of young person, solo, [realistic], rendered in blender blurry, logo, watermark, signature, cropped, out of frame, worst quality, low quality, jpeg artifacts, poorly lit, overexposed, underexposed, glitch, error, out of focus, (semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, digital art, anime, manga:1.3), amateur, (poorly drawn hands, poorly drawn face:1.2), deformed iris, deformed pupils, morbid, duplicate, mutilated, extra fingers, mutated hands, poorly drawn eyes, mutation, deformed, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, incoherent, (bad-image-v2-39000, bad_prompt_version2:0.8), bad-hands-5