I'm using a raster to SVG conversion program called "DrawingBotV3" it has some tools for filtering and converting images and uses a number of different versions of the traveling salesman algorithm.
I also am trying to create images that are especially good for conversion, in this case emulating linocut or a woodblock kind of style.
#sdxl is really very good at emulating various printing techniques.
Made with ComfyUI, the prompts are still embedded in the EXIF data in the images. It's a little less legible in A1111 but you should still be able to read them.
eerie linocut print of an stone structure in an empty field with a beam of red light emerging, floating oak trees turning into lighting, (((CMYK))), oppressive atmosphere, warfare symbolism, arcane glyphs, made of flame, hooded figures, thunder clouds, standing stones, obelisk, masterpiece, very detailed, weathered, aged, Zdislaw Beksinski, Junji Ito, ((Eyvinde Earle)), Andrew Wyeth, Francisco Goya, Moebius, psychedelic doom metal"
If anyone wants to get upset about representation, I'm literally just toggling through every ethnicity and gender except (white girl | asian girl) because there's already enough #aiartwork of them out there. It's more than just an anime generator for socially impaired nerds.
If and when we get to having full body prosthetics, people with body dysmorphia are going to come up with some absolutely wild stuff. This was intended to be an ex-military MMA fighter.
It seems probable if significant enhancement above the level of a prosthetic becomes cheap, you'll have people walking around with body parts that look like military hardware had a baby with a gaming PC..
' A booming part of tech ' (...) ' has got away with comparatively little scrutiny of its environmental impact. '
' “Fundamentally speaking, if you do want to save the planet with AI, you have to consider also the environmental footprint [of AI first],” she says. “It doesn’t make sense to burn a forest and then use AI to track deforestation.” '
@jabsonik yeah, I do individual stuff too, but I refuse to be guilted into (and these are real things I’ve seen suggested) putting fewer images on web sites or playing video games.
This model is capable of creating some extremely elaborate hairstyles and jewelry. A lot of these end up having cybernetic components, feathers, or what looks like fully functioning bird wings..
It is well researched and is a good read on its own (thx @SnoopJ).
People who follow me know that I am into generative AI, but my three strongest criticism are about data-sourcing ethics, solid user education (especially around LLMs) and building tools that centers users.
We have the opportunity to do better as an opensource community!
"Tiny Dream is a header only, dependency free #StableDiffusion 2 implementation written in C++ from scratch with primary focus on CPU performance and memory footprint. Tiny Dream runs reasonably fast on the average consumer hardware, require only 5.5 GB of RAM to execute, does not enforce Nvidia GPUs presence, and is designed to be embedded on larger codebases (host programs) with an easy to use C++ API. The possibilities are literally endless (or at least extend to the boundaries of Stable Diffusion's latent manifold)."
