Old DnD Artstyle
Priests Monsters Wizards Parameters:Positive Prompt: absurdres, masterpiece, best quality, highly detailed ,Negative prompt: bad_picturesSteps: 36, Sampler: DPM++ 2M SDE Karras, CFG scale: 7, Seed: 2814268278, Size: 512×512, Model hash: cca17b08da, Model: darkSushiMixMix_225D, Denoising strength: 0.4, Clip skip: 2, Hires upscale: 2, Hires steps: 16, Hires upscaler: 4x-UltraSharp, Version: v1.6.0-2-g4afaaf8a
SDXL Wizard Art
Parameters:Positive Prompt: (wizard:1.2) old man, black armor, red cloak, flowing, fire, (fabric with intricate pattern:1.2), (insanely detailed:1.2), ((masterpiece)), (painting:1.1), (digital painting:1.1)Negative Prompt: (worst quality:2), (low quality:2), (normal quality:2), (b&w:1.2), (black and white:1.2), (blurry:1.2), (out of frame:1.2), (ugly:1.2), (cross-eyed:1.2), (disfigured:1.2),(deformed:1.2), (extra limbs:1.2), (b&w:1.2), (blurry:1.2), (duplicate:1.2), (morbid:1.2), (mutilated:1.2), (poorly drawn hands:1.2), (poorly drawn face:1.2), (mutation:1.2), (deformed:1.2), (bad […]
SDXL Art Combination
Like previous Stable Diffusion models, you can bash photos together and then with SDX1.0 and a low denoising strength render one consistent image. Here is a funny example of this technique.Two separate pictures are combined with a tool like Photoshop: Then it’s rendered (in this case) through the Img2Img tab in Automatic1111 WebUI with a […]
NEW SDXL Generation
With recently released new model SDX1.0, generating art has never been easier, got these two from 2-3 word prompt like ‘wizard and tome’ or ‘priestess with staff’, no LORA, scripts or textual inversions! parametersPositive Prompt: magical staffNegative Prompt: text, watermark, multiple, wallpaperSteps: 20, Sampler: Euler, CFG scale: 8, Seed: 2548947855, Size: 1024×1024, Model hash: 31e35c80fc, […]
SDXL Pixel Art
Recent SDX LORAS for specific art types is so detailed its terrific, like LORA Pixel Art XL. If I had this tool when I was a Pixel asset creator my design process would’ve been perhaps ten times as fast and ten times as efficient. Parameters:Positive Prompt: wizard holding magical orb with both hands, moonlit graveyard […]
Warrior Prince
More training of my face with the LoRA Model (Low-Rank Adaptation), which allows you to use low-rank adaptation technology to quickly fine-tune diffusion models. One of the fastest, least GPU intensive training method. Parameters:poster of warrior prince <lora:Damian Lora:1>| standing on hill | centered| key visual| intricate| highly detailed| breathtaking| precise lineart| vibrant| panoramic| cinematic| […]
LoRA Model Training
Training of my face with the LoRA Model (Low-Rank Adaptation), which allows you to use low-rank adaptation technology to quickly fine-tune diffusion models. Parameters:<lora:openjourneyLora_v1:1>| ((tarot card with intricate detailed frame around the outside)) | side profile of cyberpunk head of man <lora:Damian Lora:1> with large moon in background| cyberpunk | styled in Art Nouveau | […]
AI in Art Process
AI in creative media development has indeed become a controversial topic and although I understand the plight of artists, I also understand that once Pandora’s box is opened it cannot be closed. With these changing environments one can only but adapt and implement these new tools to their design process. Here is an example of […]
Me Portrait
Portrait of myself done while learning and training with SD, plus some polish done with Photoshop. Program: Photoshop (2021)Medium: Wacom 21UX & Stable Diffusion
Medieval Goblin Sorcerer
Goblin sorcerer in medieval art style and colours. First art/asset done with the aid of Stable Diffusion, followed by touch-up in Photoshop. Game changing tool, really speeds up the illustration process… but at what cost? One thing I guarantee is that it is definitely addictive and fun. Program: Photoshop (2021)Medium: Wacom 21UX & Stable Diffusion