Flux 4K keeps coming out blurry? Swapped in a specialized VAE decoder and it's way cleaner now.

I do architectural renderings and often need to generate large images. That soft, mushy blur when Flux.1’s native VAE decodes at 4K has always been annoying—details just get flattened out. Recently I tried a VAE called UltraFlux, which is a decoder retrained on 4K high-res material, specifically aimed at large resolutions. Super easy to use: just download the file from its Hugging Face page, drop it into ComfyUI\models\vae. I renamed it UltraFlux-VAE.safetensors to keep things straight. No major workflow changes—just the usual Flux.1 Dev setup, but after the sampler, add a VAE Decode node, hook up the custom VAE, then preview.

Same latent, just swapped the decoder, and the output is noticeably sharper. Reflections on glass curtain walls, brick textures, those edge details actually hold up—Flux’s signature softness is almost gone. I haven’t even added any detailer LoRA yet, and bare output at this level is already good enough. If you want to push it further, just slap on a Flux detail LoRA after. For comparison, I used rgthree’s Image Compare node—sliding the slider back and forth makes the difference obvious.

+1, I’m literally getting wrecked by 4K blurry images right now.

So this is just swapping out the decoder, and the sampling part stays completely untouched, right? That means the cost barely goes up—total win.

Hey guys, I’ve been messing around with ComfyUI lately and I’m trying to figure out the best settings for Flux. I’ve seen a lot of people saying CFG should be around 4-6, but I’m not sure if that’s the sweet spot. Also, I’m running on 8G VRAM, so I can’t really max out everything. Any tips on getting good results without it crashing? I’m mostly doing batch generation, so I need something stable. Thanks!

Hey, quick question — does this actually help with 2k image generation, or is it only worth it for 4k?