Guys any update for H3-Regenerate-2K?
Is there any deadline or ETA you guys have for it? Also any other updates which you might want to inform us about regarding H3? Model is amazing but yeah the fast motion and other stuff is really need 2K thingy now.
The community already sorted this out to some degree. There are latent upscalers available that will take you to 2K. And even higher if you have the hardware for it.
The community already sorted this out to some degree. There are latent upscalers available that will take you to 2K. And even higher if you have the hardware for it.
I tried a lot of those but none of them worked for me, Hardware isn't issue for me, please provide me the link to the community solution you think works best, I tried Latent upscales, multi stage generation workflows and none worked for me.
The community already sorted this out to some degree. There are latent upscalers available that will take you to 2K. And even higher if you have the hardware for it.
Hey mate, Do you have a Comfyui workflow that upscales to 2K which you could share? Thanks in advance.
The community already sorted this out to some degree. There are latent upscalers available that will take you to 2K. And even higher if you have the hardware for it.
Hey mate, Do you have a Comfyui workflow that upscales to 2K which you could share? Thanks in advance.
Look into the Latent H3 Upscaler, youll need to download the safetensors and then use their example workflow and tweak the tile size and such. Its been a while since I used it and the workflow I used actually had a tiled upscaler which was easier on the vram, but I believe this was then added to the official upscaler later on. If you want to check out the old workflow which used different nodes, you can open this video that I made with it. I believe this is even a little bit over 2K. https://storage.to/G5lRkp7gT Which uses nodes from here: https://github.com/bbaudio-2025/Comfyui-MMH3-UltimateUpscale
Which was built upon the official upscaler that came first:
https://github.com/LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler