Magical Symbols and Runes Pack #Symbols #Runes #Magic #Fantasy #Gameassets #Vectorgraphics #Lowpoly #Highresolution #Png #AssetStore
https://u3dn.com/packages/magical-symbols-and-runes-pack-213858
#highresolution
YES SUCCEEDED!!!
Just rendered an image at 944×1152 (slightly above 1024×1024) using Flux1-Schnell-FP8 on my 6700 XT, and it works! (Image 1 is the Real-ESRGAN 2× upscaled version)
Workflow 1: Sampling (Image 2)
Prompt executed → UNet generates the latent
Step 1 (model load + latent generation) took 419 seconds
Output: Latent tensor saved to disk
Workflow 2 : VAE Decode (Image 3)
Latent loaded → VAE decodes the image
Duration: 7.5 seconds
Advantage: UNet doesn’t need to stay in VRAM → VRAM freed, even on 12 GB GPUs
The problem with the stock LoadLatent Node
Dropdown only shows files if they were produced / annotated by a previous SaveLatent Node
Node is designed to pass latents inside a graph, not load arbitrary files from disk
Purpose: prevents accidentally loading wrong files
Workaround (Image 4)
Edited /ComfyUI/nodes.py, class LoadLatent
Hardcoded latent path → Node now loads directly from disk
Result: Workflow 2 runs instantly, UNet can be unloaded
Timing
Step 1 (model load + latent generation): 419 s
Step 2 (VAE decode): 7.5 s
Result: High-res images on a 12 GB RDNA2 GPU are now possible on Flux1-Schnell-FP8 without ComfyUI crashing! (Image 5 is the original output)
This might actually become my new Flux workflow: render quick 512×512 previews first (which works perfectly on RDNA2 GPUs), sort out the good ones, extract the seed from the PNG metadata, and then re-render only the selected images with the same seed using the split workflow at higher resolutions. This way, high-resolution Flux1-Schnell-FP8 renders become possible on 12 GB RDNA2 GPUs D:
Question at the end: Has anyone ever done this before? Because I have no clue xD
#ComfyUI #flux #Flux1SchnellFP8 #FP8 #AMD #RDNA2 #VAE #AIArt #Pixelfed #HighResolution #GPUOptimization #LatentWorkflow #AIWorkflow #AIHacks #RealESRGAN #Upscale #AIExperiment #CreativeAI #DigitalArt #AICommunity #python #linux #opensource #foss
Just rendered an image at 944×1152 (slightly above 1024×1024) using Flux1-Schnell-FP8 on my 6700 XT, and it works! (Image 1 is the Real-ESRGAN 2× upscaled version)
Workflow 1: Sampling (Image 2)
Prompt executed → UNet generates the latent
Step 1 (model load + latent generation) took 419 seconds
Output: Latent tensor saved to disk
Workflow 2 : VAE Decode (Image 3)
Latent loaded → VAE decodes the image
Duration: 7.5 seconds
Advantage: UNet doesn’t need to stay in VRAM → VRAM freed, even on 12 GB GPUs
The problem with the stock LoadLatent Node
Dropdown only shows files if they were produced / annotated by a previous SaveLatent Node
Node is designed to pass latents inside a graph, not load arbitrary files from disk
Purpose: prevents accidentally loading wrong files
Workaround (Image 4)
Edited /ComfyUI/nodes.py, class LoadLatent
Hardcoded latent path → Node now loads directly from disk
Result: Workflow 2 runs instantly, UNet can be unloaded
Timing
Step 1 (model load + latent generation): 419 s
Step 2 (VAE decode): 7.5 s
Result: High-res images on a 12 GB RDNA2 GPU are now possible on Flux1-Schnell-FP8 without ComfyUI crashing! (Image 5 is the original output)
This might actually become my new Flux workflow: render quick 512×512 previews first (which works perfectly on RDNA2 GPUs), sort out the good ones, extract the seed from the PNG metadata, and then re-render only the selected images with the same seed using the split workflow at higher resolutions. This way, high-resolution Flux1-Schnell-FP8 renders become possible on 12 GB RDNA2 GPUs D:
Question at the end: Has anyone ever done this before? Because I have no clue xD
#ComfyUI #flux #Flux1SchnellFP8 #FP8 #AMD #RDNA2 #VAE #AIArt #Pixelfed #HighResolution #GPUOptimization #LatentWorkflow #AIWorkflow #AIHacks #RealESRGAN #Upscale #AIExperiment #CreativeAI #DigitalArt #AICommunity #python #linux #opensource #foss
Die Architektur der Pose. In dieser Aufnahme stand die Symmetrie und die Spannung der Linien im Vordergrund. Als Fotograf ist es faszinierend zu sehen, wie das gerichtete Studiolicht die Textur des metallischen Lila-Tops zum Leuchten bringt und gleichzeitig die athletische Definition präzise herausarbeitet. Ein minimalistisches Setup, das den Fokus voll und ganz auf die Form und den künstlerischen Ausdruck lenkt.
#StudioPhotography #PortraitPhotography #LightingDesign #CommercialPhotography #SharpFocus #ColorGrading #StrobeLighting
#HighResolution #PhotographyTechnique #CleanComposition #StudioLight #MetallicPurple #VibrantColors #PinkHairDon'tCare
#FashionEditorial #MinimalistBackground #Contrast #GlossyLook
#VisualArt #Flexibility #Vertic
#StudioPhotography #PortraitPhotography #LightingDesign #CommercialPhotography #SharpFocus #ColorGrading #StrobeLighting
#HighResolution #PhotographyTechnique #CleanComposition #StudioLight #MetallicPurple #VibrantColors #PinkHairDon'tCare
#FashionEditorial #MinimalistBackground #Contrast #GlossyLook
#VisualArt #Flexibility #Vertic
🎉 Behold! The LG UltraFine Evo 6K 32-inch Monitor: because who doesn't want to mortgage their house for pixels you can't even see? 🙄 Enjoy the thrill of paying extra for a screen that screams, "Look at me, I'm fancy!" while offering more resolution than your eyes could ever appreciate. 💸👀
https://www.wired.com/review/lg-ultrafine-evo-6k-32-inch-monitor/ #LGUltraFineEvo6K #FancyMonitor #OverpricedTech #HighResolution #PixelsYouCantSee #HackerNews #ngated
High Resolution Simulation Of Urban Compound Flooding Under Climate Impacts
--
https://doi.org/10.1016/j.uclim.2026.102771 <-- shared paper
--
#ClimateChange #FloodResilience #UrbanPlanning #ClimateAdaptation #HydrodynamicModeling #CompoundFlooding #SeaLevelRise #sealevel #Flood #flooding #depth #hazard #risk #riskassessment #Urban #urbanplanning #resilience #NewYorkCity #NYC #Hoboken #NewJersey #infrastructure #damage #cost #economics #vulnerability #urban #hydrodynamic #city #cities #climatechange #extremeweather #model #modeling #spatial #GIS #mapping #spatialanalysis #spatiotemporal #highresolution #pluvia #rainfall #precipitation #fluvial #HurricaneIda #stormsurge #building #structures #topography #drainagesystems #infiltration #emergencyservices #framework #workflow #methodology
Marriott International | Gastronomy at W Rome: Educated Cuisine, Amazing Pastry And Alchemical Mixology
Thanks to an exemplary fusion between Sicilian cuisine and the culture …
#dining #cooking #diet #food #ItalianRegionalCuisine #Brand #highresolution #imagedownloads #imagelibrary #images #Italia #Italian #italiano #italy #media #press #regionalcuisine
https://www.diningandcooking.com/2464235/marriott-international-gastronomy-at-w-rome-educated-cuisine-amazing-pastry-and-alchemical-mixology-2/
Tip du jour : vous souhaitez télécharger le logo d'une entreprise en haute résolution ? Oubliez Google, Bing. Ce site fait pas mal l'affaire :
Seoul weighs approval for Google, Apple high-resolution map requests
@sjolsen not really, cuz if @tantacrul evidenced one thing, it's that #UI & #UX can be quantified as "good" and/or "bad" and actually implement the best possible option given the workflows at hand (conversely to what @landley once said: #FLOSS can do UI & UX; [tho he also said that consistency is key and #Tantacrul certainly does not just design but also tests this designs more thoroughly than most GAFAMs do their products...])
- And I do have to give him credit for modernizing applications that indeed need some overhaul, as #Audacity did look like something from #Windows95, #macOS9 or #Amiga (and we all can agree that any application from back then that's still around regardless if #Photoshop, #Cubase or even #Sibelius had to move on and change…).
Personally I do hate the #RibbonUI because it's wasteful in terms of screen space and demands way more clicks and mouse travel in my workflows.
Waiting for a consumer oriented digital large format camera.
#cameras #photography #largeformatcameras #largeformatphotography #largeformatfilm #digitalcameras #digitalbacks #imagingsensors #highresolution
#ai #aiArt #aiArtWork #Cute #O #YellowFur #Fluffy #Realistic #LightAndColor #SoftGradient #PastelColors #SoftLighting #HighResolution #Honeycore #ai #aiArt #aiArtWork #Cute #YellowFur #RealisticLight #PastelColors #Honeycore #HighResolution #SoftLighting
A park inside a park near a bunker in #Braunschweig #landscape #panorama #gigapixel #photostitching #woods #deepinthewoods #photography #parkwood #darktrees #lightvsdark #naturephotography #woodlandphotography #treeportrait #woodlandbeauty #capturethelight #naturalbeauty #landscapephotography #gigapixel #photostitching #panoramicview #sceniclandscape #highresolution #naturephotography #visualartistry
#Meta’s #Tiramisu prototype #VRheadset boasts 90 PPD resolution, 1400 nits brightness, and three times the contrast of Quest 3. While its narrow 33° field of view limits practicality, the stunning visual quality, with no pixelation or aliasing, showcases the impact of #highresolution and #brightness on #realism. https://www.uploadvr.com/meta-tiramisu-hyperrealistic-vr-hands-on/?Metaver.se #Metaverse #VirtualWorlds #XR #VR #MR #AR #BeyondPictures
#Meta’s #Tiramisu prototype #VRheadset boasts 90 PPD resolution, 1400 nits brightness, and three times the contrast of Quest 3. While its narrow 33° field of view limits practicality, the stunning visual quality, with no pixelation or aliasing, showcases the impact of #highresolution and #brightness on #realism. https://www.uploadvr.com/meta-tiramisu-hyperrealistic-vr-hands-on/?eicker.news #tech #media #news
#ai #aiArt #aiArtWork #WaterShield #DynamicWater #ProtectiveArc #GlossyTexture #Hydration #BarrierStructure #Photorealistic #VibrantLighting #SoftBlueTones #GentleRipples #ai #aiArt #aiArtWork #water #shield #protection #fluid #photorealistic #transparency #dynamic #splashes #ripples #highresolution #vibrantlighting #smoothcurves
ADS1115 ADC in Qwiic/Stemma QT Form #TindieBlog #ADS1115 #HighResolution #ADC #Qwiic #StemmaQT #LowPower
https://blog.tindie.com/2025/07/ads1115-adc-in-qwiic-stemma-qt-form/
Client Info
Server: https://mastodon.social
Version: 2025.07
Repository: https://github.com/cyevgeniy/lmst