I want AI (Artificial Intelligence) to generate images in my style, both for me and anyone else. And this might be art too -- according to Essentialism.
Leonardo.AI (YouTube) generates images in MY DRAWING STYLE after it trained on 30 drawings from my book :
The images from the video above are posted on these two web pages:
Only Midjourney allows me to upload two images and "Blend" them, which is a great feature. Yet Midjouney's NSFW filter is way too sensitive, and will NOT usually allow me to upload and blend my Figure Drawings. So there is no good way to generate and blend images in Midjourney with my drawing style.
OpenArt however would accept my figure drawings. Therefore last December 2022 I trained a model on my drawings, using their Photo Booth feature. While OpenArt then generated images in my drawing style, it was limited to just figures of women (like the source images it trained on). For instance note the single figure below -- generated with the prompt: "woman riding a rhinoceros" -- but sans rhinoceros:
Albeit limited, the OpenArt results worked to make a laser engraved print:
- model_20221213233657.ckpt (2 GB)
I was inspired to share that model, which one can do by uploading to CIVITAI (though I did not).
Back in 2020 I did share an AI model that I made in made in Runway ML based on my drawing style. This month I discovered that my model was used as part of a large AI projection project -- AUTOLUME ACEDIA -- in Kelowna, British Columbia, Canada, last February 2022:
I had uploaded that previous 2020 model to Justin Pinkney's Github:
- Long_Krrrl_Drawings__final.pkl (364 MB)
Ultimately I chose share my drawing style inside Leonardo.AI. That website allows me to make AI models based on my figure drawings, and share my model with the rest of their users. My "Krrrl Lines 06" model was trained on PG images -- which I made it "public," so that everybody can generate images in my KRRRL drawing style. I can't download that AI model and post it on CIVITAI however.
LEONARDO.AI Images
Naturally I went crazy this month generating images in my drawing style while the service is still free (after getting access on February 18th):
altered with AI model: "Krrrl Drawings 01"
Other people on Leonardo.AI also generated images from the AI model based on my KRRRL drawing style:
I even generated a linocut image with Leonardo.AI, and laser engraved it into linoleum at Quelab, and printed it at Henry Morales' studio:
OTHER AI Programs
I also paid for a Pro subscription to Mage.Space. I can upload my figure drawings and Mage.Space will alter them. While this online program will generate AI images for free, one needs a subscription to use all 36 models (plus with a subscription there is no problem with NSFW). I get the most out of their "Pix2Pix" and "ControlNet" -- which they added on February 26th -- especially "ControlNet Canny,"
Blue Willow is free and works inside Discord, like Midjourney. While it's quicker than Midjourney, the results are not always as pretty:
DEZGO is free, and no sign up is required. It allows one to upload and alter an image (and does not have an NSFW filter):
smoothed out the input Midjourney generation on the left
HOLOGRAMS
RGBD PHOTO will convert a 2D image into a diptych-with-a-depth-map -- which turns into a hologram when uploaded to the Looking Glass Portrait display. I converted and uploaded the images into HOP files, and then posted the HOLOGRAM slideshows on my GDrive, for anyone to download:
- HOLOGRAM Slideshow:
- 230214__HOP.zip (38.14 MB)
- HOLOGRAM Slideshow:
- 230218__KRRRL_holograms.zip (31 MB)
- HOLOGRAM Slideshow:
- 232020__HOP.zip (15 MB)
Hologram files can be downloaded from the following GDrive folders:
- I asked about sharing slideshows on the Looking Glass Discord.
My Leonardo.AI Models
Leonardo list of all my AI models
trained in February 2023
1) Krrrl Drawings 01 -- I trained the first model on 30 Drawings from my book "Finish My Figure Drawings":
Figures: 001, 002, 005, 006, 007, 013, 014, 015, 018, 019; 021, 025, 026, 030, 033, 034, 039; 043, 044, 045, 046, 049, 050, 052, 053, 054, 056, 057, 058, 059
Krrrl Paintings
instance prompt: "Krrrlpaint"
Generated with
"Krrrrl Paintings"
4) Krrrl Drawings 04 -- I trained the fourth model on 30 Drawings from my book "Finish My Figure Drawings":
Figures: 061, 062, 065, 068, 072, 073, 074, 080; 082, 084, 085, 088, 089, 90, 94, 95, 98, 100; 101, 103, 105, 109, 111, 113, 114, 115, 119
Krrrl Drawings 04
instance prompt: "Krrrl04"
Krrrl Pencil and Ink 05
instance prompt: "Krrrl5"
6) Krrrl Lines 06 -- I trained the sixth model on 30 PG generations made from the first and fourth models, based on the drawings of my book. Since all the data images were safe-for-work, I made this model public, so that other users on Leonardo.AI can generate images based on my drawings:
Krrrl Lines 06
instance prompt: "KrrrlLines"
*The PG model
that I offered to the public*
- The first model -- Krrrl Drawings 01 -- generates the best images.
VECTORIZING
Since I was drawing in pencil and ink I thought those drawings might translate well into vector files:
Download all the SVG vector files from this post:
230277_Vector_drawings.zip (424 KB).
NOTABLE
The AI Art controversy flared up in the Netherlands, when the original "Girl with a Pearl Earring" was replaced with an AI version. The original was loaned out for a big Vermeer exhibition at the Rijksmuseum in Amsterdam, so the Mauritshuis Museum had an Open Call to artists for variations of the painting -- five of the 3,482 entries were chosen to hang in the museum. While the AI version apparently was the grand winner, a photo by Vallarie Enriquez of El Paso of her husband Arturo, was one of the five chosen versions:
Meanwhile the Iron Man sculpture met his match on February 27th, when a truck ran into him on Lomas at 4th. The Iron Man faced off with three justice buildings, on other three corners of this intersection in Albuquerque:
I always find it ironic that at least one of the justice buildings was a crime, as the mayor and head of the state senate skimmed off a lot of graft from its construction. Maybe that is what the Iron Man was standing up against:
Wikipedia: "From 2005 to 2009, the Metro Courthouse was at the center of a high-profile fraud investigation, during which allegations emerged that a group of conspirators had siphoned off $4.2 million from the courthouse construction project in a scheme described by the Albuquerque Journal as "breathtaking in scope and star power." Eight people were eventually named as defendants in the case, including the former president pro tempore of the New Mexico State Senate and a former mayor of Albuquerque. The investigation ended with six of the accused pleading guilty to conspiracy and mail fraud, while the other two pleaded guilty to misprision of felony. "
PROGRAMS
I note that MattVidPro AI is from Albuquerque, according to his Twitter.
- Leonardo.AI
- Midjourney
- Deep Dream Generator
- DALL-E 2
- Mage.Space
- Open Art
- Runway ML
- Blue Willow
- Dezgo
- Scribble Diffusion
- Lexica
- Playground AI
- AI Background Generator
- Skybox (360 AI scenes) YouTube
- CIVITAI
- Future Tools
- Futurepedia
- Pharmapyschotic -- Tools and Resources for AI Art
- V4 Midjourney Reference Sheets (YouTube)
- Petalica Paint
- Palette FM
- Paint 3D
- Point-e Demo
- Point-E text-to-3D Demo
- Stable Attribution
- InstructPix2Pix (added to Mage.Space)
- Hugging Face: Img2Img Stable Diffusion CPU
- Hugging Face: Instruct-Pix2Pix Diffusion
- Hugging Face: ControlNet
- Hugging Face: Thin-Plate Spline Motion Model for Image Animation
- Hugging Face: TEXTure (does not work for me)
- nightmareair/real-esrgan (enlarges the resolution)
- Upscale Media
- WebXR
- RGBD PHOTO
- Hugging Face: RGB to RGBD for Looking Glass (using MiDaS)
- Looking Gloves
- Mobile Monocular
- Cleanup Pictures
- EzGif
- Inkscape
- XnView
- Blender
- Font Generator
- Pine Tools -- Sharpen Image Online
- LunaPic
- MakeSweet
- Photo 505
- YouTube: InvokeAI - Load your Custom Models / Stable Diffusion 1.x
- Volograms
- YouTube: PhysDiff: Physics-Guided Human Motion Diffusion Model
Other Art Program Lists:
- Plus there are a lot of AI programs listed on my last January 31, 2023 post -- Entering: The Year of the Rabbit Hole
- And a summary post from last year -- AI Programs -- and other online art websites
Vision
No comments:
Post a Comment
Note: only a member of this blog may post a comment.