City
City
If you send me a sample workflow I can check it out. I'm currently trying to further finetune the upscaler. It looks like I'll be able to fix the odd...
I think your main problem is that your first advanced K-sampler doesn't return the leftover noise. I don't think you can avoid doing that, even if you inject your own...
>Using your latent interposer to do xl->1.5 -> upscale -> 1.5->xl made it better but so far my results are either blurry or having some sort of scanlines. How the...
Just a quick heads-up, I re-did all the models on the upscaler. Completely new model arch and training code so image quality is a lot better now. A simple git...
@ntdviet Sorry, I saw you started the proper discussion but didn't have the time to post it there as well. I'm glad it works, it seems a lot more flexible...
@suede299 If I understand correctly, your main problem is that after the upscale the image doesn't align properly to 1920x1080 (e.g. downscaling would make it blurry)? The only thing I...
Doesn't this also just use the SDXL VAE? Selecting XL should make it work. https://huggingface.co/fal/AuraFlow/blob/main/vae/diffusion_pytorch_model.fp16.safetensors https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/vae/diffusion_pytorch_model.fp16.safetensors
This repo is only for converting the latents between models for doing img2img on the output of one model with a second model that uses a different latent space. What...
Update ComfyUI itself, it should be fixed now.
@Creepybits Did you do a fresh git pull?