~Helen Parr~ by Ken1171_Designs
Close
Hover over top left image to zoom.
Click anywhere to exit.
Members remain the original copyright holder in all their materials here at Renderosity. Use of any of their material inconsistent with the terms and conditions set forth is prohibited and is considered an infringement of the copyrights of the respective holders unless specially stated otherwise.
Description
My fanart of Helen Parr, the Elastigirl from The Incredibles Disney movies, voiced by the incredible Holly Hunter. Image composed with Stable Diffusion and Paintshop.
Comments (4)
leeduva
Nice!!!!!
Ken1171_Designs
Thank you! Back in the day, I bought the DVDs from both movies. ^__^
Darkglass
Quality piece of sophisticated fan art...!!, first class work on this, doubt this was very easy to achieve, hopefully its not just one of them....randomly generated images and this is what you worked towards, whatever the case...its a like and fav for me...!!
Ken1171_Designs
Thank you! I have been an artist for 17 years, and AI, like other tools, start with an empty canvas. And also, like other tools, the more I use it, the better I am getting with it. ^___^
Darkglass
Well 25+ Years in and Still learning...and AI...is just a tool to curb the creative enthusiasm, things i simply don't have time to spend a hundred hours on only to be overlooked...
Ken1171_Designs
I believe good artists will never be overlooked, no matter what tools they use. ^____^
MollyFootman Online Now!
Wow! This looks like a frame out of a Pixar movie (with the requisite Ken amplification of sexy ;-P). I am still messing about with Stable Diffusion but have nothing worth sharing. I expect that I need to give more time and thought to the prompts I am using.
Molly
Ken1171_Designs
Thanks Molly! When it comes to SD, composing a prompt is an art on its own right. Different AI models respond differently to certain words, so we can't always use the same prompts. How a model responds to specific words depends on how it was trained. Since this is an LLM (Large Language Model), the trick is to find out what words work the best in MOST models, and at the same time try to remember what words work best with specific models. The latest SD interface allows storing full or partial prompt presets, so we can reuse and mix them depending on the model we are working on. This is especially useful for negative prompts, because those will work with most AI models. And then comes the weight balancing when working with LoRAs. That can be really hard when most AI models (LoRAs included) are overfit when trained. Balancing the weights with multiple LoRAs can be an exercise in patience. And then come the extensions, inpainting, outpainting, img2img, and ControlNet. Almost every day they come up with something new. I don't remember any software ever being updated or expanded like this. ^___^