#sdxl — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #sdxl, aggregated by home.social.
-
La semana pasada, logré uno de las fantasías mal vista y a veces ilegales de los artistas, clásicos y de #IA...
La autoinserción del mismo en sus obras
Logré hacer un #LoRA para #SDXL en el que por fin podemos convivir mi pareja y yo
Con todo lo que implica, y todas las posibilidades que abre
Aún no es perfecto, estoy buscando el punto dulce para no sobrecocinarlo o dejar crudo el modelo
-
La semana pasada, logré uno de las fantasías mal vista y a veces ilegales de los artistas, clásicos y de #IA...
La autoinserción del mismo en sus obras
Logré hacer un #LoRA para #SDXL en el que por fin podemos convivir mi pareja y yo
Con todo lo que implica, y todas las posibilidades que abre
Aún no es perfecto, estoy buscando el punto dulce para no sobrecocinarlo o dejar crudo el modelo
-
Почему диффузия рисует швы на 40-мегапиксельных фото и как сделать тайлы с памятью
У видео-моделей есть память между кадрами. У диффузионных фото-моделей - нет. Именно поэтому стандартный тайлинг профессиональных кадров на 40-150 мегапикселей всегда даёт лестницу швов на градиенте неба, плывущий цвет на коже и драматический перепад текстур на границах тайлов. Я двадцать лет работаю ретушёром и четвёртый год пытаюсь это починить, приспособить диффузионки к профессиональной съёмке. Все эти годы любой подход, что мой, что чужой, крутится вокруг одного: режем картинку на 100+ тайлов, обрабатываем каждый отдельно, склеиваем обратно. И каждый раз вылезает то же самое - тайлы не согласовываются между собой. В статье разбираю три идеи о том, как у фото-модели может появиться память между соседями. Восемь архитектурных классов памяти из видео-диффузии (BCLA из SANA-Video, FramePack, SVD reshape, AnimateDiff и другие): какие переносятся на тайлы, какие нет и почему.
https://habr.com/ru/articles/1028252/
#диффузионные_модели #тайлинг #ретушь #SANA #видеодиффузия #sdxl #flux
-
-
-
Little update on my #neuralnetwork #experiment: Something happened. What happened is hard to say so far. The motionnet model was only trained on 3 videos for 2000 steps. One of the videos was a butterfly on a flower. (You can see it attached).
So this is the first actual test I've run successfully on the full pipeline. The prompt: A butterfly on a flower.
You can see the first frame (generated by #SDXL weights) and the generated #video.
-
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.
-
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.
-
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.
-
Why is he wet? :pepe_sweat:
-
Why is he wet? :pepe_sweat:
-
🇺🇸 🇺🇸 🇺🇸 🦅🦅🦅 :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: 🦅🦅🦅🇺🇸 🇺🇸 🇺🇸
-
🇺🇸 🇺🇸 🇺🇸 🦅🦅🦅 :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: :hoggers: 🦅🦅🦅🇺🇸 🇺🇸 🇺🇸
-
🙌 Just completed: our Invoke.AI video tutorial series by Robert Kremer of the AI + D Lab at HfG Schwäbisch Gmünd! Learn how to use Invoke AI + Stable Diffusion XL – from installation to inpainting, depth maps, regional guidance and more. 🎨🔥 https://aid-lab.hfg-gmuend.de/articles/invoke-ai-tutorial-series/
#InvokeAI #SDXL #Tutorial #genAI #KITeGG -
🙌 Just completed: our Invoke.AI video tutorial series by Robert Kremer of the AI + D Lab at HfG Schwäbisch Gmünd! Learn how to use Invoke AI + Stable Diffusion XL – from installation to inpainting, depth maps, regional guidance and more. 🎨🔥 https://aid-lab.hfg-gmuend.de/articles/invoke-ai-tutorial-series/
#InvokeAI #SDXL #Tutorial #genAI #KITeGG -
the prompt for this one was "jerkin muh gerkin" and i dont even know man. ai is weird.
#ai #stablediffusion #sdxl #jerkinmuhgerkin #gottagofast #sonic
-
the prompt for this one was "jerkin muh gerkin" and i dont even know man. ai is weird.
#ai #stablediffusion #sdxl #jerkinmuhgerkin #gottagofast #sonic
-
The automated pepe-bot has been killing it lately.
-
The automated pepe-bot has been killing it lately.
-
What was this an ad for?
#pepe #pepethefrog #ai #aiart #stablediffusion #sdxl #bot #ad
-
What was this an ad for?
#pepe #pepethefrog #ai #aiart #stablediffusion #sdxl #bot #ad
-
🧑💻 #IA / Génération d’images
🐯 « En passant – #SDXL dans #Vittascience et dans #ComfyUI : variations sur la #guidance » – À quoi ce réglage censé réguler l’influence des instructions textuelles sur les images générées correspond-il réellement ?
-
"Overdressed? Maybe. But I'm not the one here who complains about the weather..."
#aiart #StableDiffusion #sdxl #puffer #snowsuit #moonboots -
Fire Walk with Me https://youtube.com/shorts/qK7A0BKAfMU?si=JtD-2NNEnSeeXsaV via @youtube #1080p #60fps, #UHD, #DavidLynch, #TwinPeaks, #BlackLodge, #FWWM, #surrealism, #nightmare, #enigmatic, #haunting, #cinematic, #visual, #artistic, #tribute, #homage, #CultClassic #horror, #animation, #SDXL, #FLUX, #comfyui, #LivePortrait, #shortfilm
-
Fire Walk with Me https://youtube.com/shorts/qK7A0BKAfMU?si=JtD-2NNEnSeeXsaV via @youtube #1080p #60fps, #UHD, #DavidLynch, #TwinPeaks, #BlackLodge, #FWWM, #surrealism, #nightmare, #enigmatic, #haunting, #cinematic, #visual, #artistic, #tribute, #homage, #CultClassic #horror, #animation, #SDXL, #FLUX, #comfyui, #LivePortrait, #shortfilm
