#stablediffusionxl — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #stablediffusionxl, aggregated by home.social.
-
Been messing around with a little #prototype #neuralnetwork. It behaves similarly to a #video #codec. It uses a frozen set of weights from #StableDiffusionXL and uses its latent space to carry forward to a set of networks that behave like the B-frame motion vectors used by codecs like #MPEG. These are smaller networks, letting me train it on my regular old #GPU while relying on the work of the big boys for generating I-frames via #SDXL.
At least that's the theory. Reality remains to be seen.
-
Been messing around with a little #prototype #neuralnetwork. It behaves similarly to a #video #codec. It uses a frozen set of weights from #StableDiffusionXL and uses its latent space to carry forward to a set of networks that behave like the B-frame motion vectors used by codecs like #MPEG. These are smaller networks, letting me train it on my regular old #GPU while relying on the work of the big boys for generating I-frames via #SDXL.
At least that's the theory. Reality remains to be seen.
-
Stability announces Stable Diffusion 3, a next-gen AI image generator - Enlarge / Stable Diffusion 3 generation with the prompt: studio photogr... - https://arstechnica.com/?p=2005341 #aiimagegenerators #stablediffusionxl #stablediffusion3 #machinelearning #sourceavailable #stablediffusion #imagesynthesis #emadmostaque #openweights #stabilityai #deepfakes #dall-e3 #biz #dall-e #openai #sdxl #ai
-
Stability announces Stable Diffusion 3, a next-gen AI image generator - Enlarge / Stable Diffusion 3 generation with the prompt: studio photogr... - https://arstechnica.com/?p=2005341 #aiimagegenerators #stablediffusionxl #stablediffusion3 #machinelearning #sourceavailable #stablediffusion #imagesynthesis #emadmostaque #openweights #stabilityai #deepfakes #dall-e3 #biz #dall-e #openai #sdxl #ai
-
#портрет #NeuralNetwork #DALLE3 #StableDiffusionXL #aiart #TRH
В предыдущем посте я наврал, Там Stable Diffusion XL. Но разницы между ним и DALL-E 3, по-моему, определить очень сложно.
-
#industrial #design #car #concept
An old model made with #b3d and elaborated with #AI #StableDiffusionXL -
https://huggingface.co/spaces/ArtGAN/Diffusion-API
I tried #StableDiffusionXL with nodes, which you can find at this link, a small video showing the nodes used, I hope it can be useful
I set up the network control with my own drawing and for me it is simpler than using #LeonardoAI -
Old design project iterated with #StableDiffusionXL and control net feature. #boat #Design #sailboat
-
I can't stop processing images with control net and #StableDiffusionXL. also this is done from a #Lineart done in #Blender with #Greasepencil from my my own model. #b3d #blender3d
-
Anyway the use of the control net make your own drawing better and without #copyright infringements. I think this is the best way to use the #AI. #StableDiffusionXL Image source from a #Blender model rendered only with the use of #LineArt and #GreasePencil #b3d #blender3d
-
Anyway the use of the control net make your own drawing better and without #copyright infringements. I think this is the best way to use the #AI. #StableDiffusionXL Image source from a #Blender model rendered only with the use of #LineArt and #GreasePencil #b3d #blender3d
-
Поставил себе #StableDiffusionXL в #InvokeAI, который с кофмортом генерирует картинки 1024x1024, щёлкнул галочки "seamless X" и "seamless Y" (чтобы картинкой можно было замостить любую поверхность) и получил несколько довольно приятных обоин для своего довольно кривого многомониторного пространства.
Эстетически эффект близкий, а генерировать гораздо проще, чем полотно 4720x1920 без повторов. Разглядыванием обоев рабочего стола я всё-таки не занимаюсь, как оказалось.
-
Поставил себе #StableDiffusionXL в #InvokeAI, который с кофмортом генерирует картинки 1024x1024, щёлкнул галочки "seamless X" и "seamless Y" (чтобы картинкой можно было замостить любую поверхность) и получил несколько довольно приятных обоин для своего довольно кривого многомониторного пространства.
Эстетически эффект близкий, а генерировать гораздо проще, чем полотно 4720x1920 без повторов. Разглядыванием обоев рабочего стола я всё-таки не занимаюсь, как оказалось.
-
My first attempts at using Stable Diffusion XL locally (no server or internet connection necessary) ...
-
My first attempts at using Stable Diffusion XL locally (no server or internet connection necessary) ...
-
Делаем аватарки для девочек из Мастодона. Если лениво (или не получается) зарегистрироваться — просто оставляйте ник в каментах.
Making avatars for Mastodon girls. If you’re too lazy (or can’t) to register, just leave your nickname in the comments.
#MastoArt #AIArt #Mastodon #aiphoria #NeuralNetwork #DALLE3 #stablediffusionxl
https://beta.aiphoria.world/community/chat/658839bb04a28450a13f91c9
-
Делаем аватарки для девочек из Мастодона. Если лениво (или не получается) зарегистрироваться — просто оставляйте ник в каментах.
Making avatars for Mastodon girls. If you’re too lazy (or can’t) to register, just leave your nickname in the comments.
#MastoArt #AIArt #Mastodon #aiphoria #NeuralNetwork #DALLE3 #stablediffusionxl
https://beta.aiphoria.world/community/chat/658839bb04a28450a13f91c9
-
Вроде открылась для регистрации новая #СоциальнаяСеть https://beta.aiphoria.world/
Посты писать нельзя. Каментить нельзя 😉 Есть #ChatGPT 4, ChatGPT 3.5, #DALL-E 2, DALL-E 3, #StableDiffusionXL, Stable Diffustion 2.1 и какие-то еще для генерации музыки. Вот результаты генерации как раз можно выкладывать и лайкать.
Присоединяйтесь, в общем ;-)
-
#NeuralNetwork #ВеселыеКартинки
Господа! Я взоржал аки конь, когда, проверяя, знает ли #StableDiffusionXL нашего всенародно любимого (непонятно, правда, за что) персонажа, получил ЭТО. Встречайте: ЧЕБУСРАКА 🤣 -
Stable Diffusion Turbo XL can generate AI images as fast as you can type - Enlarge / Example images generated using Stable Diffusion XL Turbo. (cr... - https://arstechnica.com/?p=1987046 #stablediffusionxlturbo #stablediffusionxl #machinelearning #stablediffusion #imagesynthesis #stabilityai #biz #sdxl #ai
-
Stable Diffusion Turbo XL can generate AI images as fast as you can type - Enlarge / Example images generated using Stable Diffusion XL Turbo. (cr... - https://arstechnica.com/?p=1987046 #stablediffusionxlturbo #stablediffusionxl #machinelearning #stablediffusion #imagesynthesis #stabilityai #biz #sdxl #ai
-
Ars Technica: Stable Diffusion Turbo XL can generate AI images as fast as you can type https://arstechnica.com/?p=1987046 #Tech #arstechnica #IT #Technology #StableDiffusionXLTurbo #StableDiffusionXL #machinelearning #StableDiffusion #imagesynthesis #StabilityAI #Biz&IT #SDXL #AI
-
It's kind of funny how machine-learning AI works. If you feed Stable Diffusion XL "Pale woman,mirror,reflection" the result has no mirror or reflection. If you prompt it with "woman, mirror, reflection", there she is looking into a mirror. Of course, SDXL doesn't know how mirrors work, so the reflection doesn't match the original closely, but it's recognizably the same woman in the same dress. Interesting, SDXL gets depth-of-field right in this image.
-
Memento mori, mis amores.
-
Memento mori, mis amores.
-
CW: Risque AI Ghost Images
I'm starting to play around with ghostly figures for my Halloween generations. Fooocus is making lots of changes lately and I decided to play around with "realism" mode.
I liked the results, thought they are a tad thirsty...
#aiart #Fooocus #stablediffusion #stablediffusionXL #generativeart
-
CW: Risque AI Ghost Images
I'm starting to play around with ghostly figures for my Halloween generations. Fooocus is making lots of changes lately and I decided to play around with "realism" mode.
I liked the results, thought they are a tad thirsty...
#aiart #Fooocus #stablediffusion #stablediffusionXL #generativeart
-
Anime villains inspired by "the big 3" in the US.
One who is blue, another who is red, and another that's magenta. Who could they be...?
-
Anime villains inspired by "the big 3" in the US.
One who is blue, another who is red, and another that's magenta. Who could they be...?
-
CW: AI generated imagery
Since the Stable Horde bot is still down, I'll have to use external platforms to generate images.
Here's SDXL from Clipdrop, prompt: Limits to Growth, climate catastrophe, extinction event, ecology falling apart, biosphere degradation, collapse of the economy, collapse of civilisation, extreme weather, weird world, invasive species, dying forests, wildfires, superweeds, heat death, ecological apocalypse#aiart #aigenerated #stablediffusion #stablediffusionxl #sdxl
-
CW: AI generated imagery
Since the Stable Horde bot is still down, I'll have to use external platforms to generate images.
Here's SDXL from Clipdrop, prompt: Limits to Growth, climate catastrophe, extinction event, ecology falling apart, biosphere degradation, collapse of the economy, collapse of civilisation, extreme weather, weird world, invasive species, dying forests, wildfires, superweeds, heat death, ecological apocalypse#aiart #aigenerated #stablediffusion #stablediffusionxl #sdxl
-
Selbermalen ist out: Heute durfte #StableDiffusionXL sich an Wasserfarben versuchen. Während die mit dem Base-Modell erzeugte Fassung nur okayish war, sieht das mit dem Refiner-Model überarbeitete Bild doch hübsch aus. #stablediffusion #KI
-
Selbermalen ist out: Heute durfte #StableDiffusionXL sich an Wasserfarben versuchen. Während die mit dem Base-Modell erzeugte Fassung nur okayish war, sieht das mit dem Refiner-Model überarbeitete Bild doch hübsch aus. #stablediffusion #KI
-
CW: AI generated pop surrealism
Since the Stable Horde bot doesn't offer SDXL anymore, I've been using Clipdrop instead.
#aigenerated #aiart #stablediffusion #stablediffusionxl #sdxl #surrealism #popsurrealism #elektrodada -
CW: AI generated pop surrealism
Since the Stable Horde bot doesn't offer SDXL anymore, I've been using Clipdrop instead.
#aigenerated #aiart #stablediffusion #stablediffusionxl #sdxl #surrealism #popsurrealism #elektrodada -
Der Pinguin des Tages ist der erste seiner Art, der mit #StableDiffusionXL auf meinem Rechner erzeugt wurde. Und er ist ziemlich hübsch geworden.
-
Der Pinguin des Tages ist der erste seiner Art, der mit #StableDiffusionXL auf meinem Rechner erzeugt wurde. Und er ist ziemlich hübsch geworden.
-
My new #musicvideo with #Plazmapunk
#StableDiffusionXL #Kandinsky2_2
Enjoy it! 😎✌️Artist: Mike Huckebein
Title: Crazy Piano
Genre: Strommusik / Techno House
Video: Plazmapunk
Model: Stable Diffusion XL / Kandinsky 2.2
Video Editor: Cap Cut -
@Arkhamrefugee Suggestion taken and used. How'd I do?
#StableDiffusion #sdxl #comfyUI #stablediffusionXL #aiartcommunity #aiart #ai
-
I had a friend say my Harrison Ford #aiart images lacked aggressive enough finger pointing.
Enjoy some more #wallpaper #art for you all. This time with 100% more pointing!
#StableDiffusion #sdxl #comfyUI #stablediffusionXL #aiartcommunity
-
El nuevo #StablediffusionXL se ve bien. Esta es la imagen de "perro comiéndose su propia pierna".
-
Also, only have had a little time to try out the SDXL 1.0 release. That said, good stuff!
Can't wait to see what dreams we can make come true with it!
-
