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

Rendered Garfield images using Flux on my RX 6700 XT.
Includes both fully 3D and classic comic style bench-press scenes.
Upscaled the outputs with Real-ESRGAN

#Garfield #Comics #3DKunst #RealESRGAN #Katze #DigitalArt #3D #FluxAI #3DArt #Upscale #Cat #3DRendering #RX6700XT #Flux #aiart #LocalAI

FOSS Advent Calendar - Door 7: Enhancing Images with Real-ESRGAN

Today we explore Real-ESRGAN, a powerful FOSS tool for upscaling and improving image quality.

The name stands for Enhanced Super-Resolution Generative Adversarial Networks, highlighting the AI-powered approach behind the magic.

Real-ESRGAN can take a low-resolution or slightly blurry image and enhance it, adding details that make it look sharper and more natural. It works via the command line, where you provide an input image and get an upscaled output image. You can instantly compare the results in your favorite image viewer, like EOG.

It’s perfect for nerds, FOSS enthusiasts, or anyone who wants to improve images without relying on commercial software.

Pro tip: try upscaling an old screenshot or a tiny meme, the results are often hilarious and impressive at the same time!

Link: https://github.com/xinntao/Real-ESRGAN

Which old or low-res image would you love to upscale with Real-ESRGAN?

#FOSS #OpenSource #Linux #CLI #Terminal #RealESRGAN #AI #ImageEnhancement #SuperResolution #NerdContent #AdventCalendar #OpenTools #FOSSAdvent #Upscale #GAN #Artificialtelligence #ImageProcessing #TechNerds #CommandLine #Fediverse #OpenTools #adventkalender #adventskalender