multidiffusion-upscaler-for-automatic1111
multidiffusion-upscaler-for-automatic1111 copied to clipboard
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Why this error occurs?
Upscaling image with BSRGAN... LoRA weight_unet: 0.3, weight_tenc: 0.3, model: ligneClaireStyleCogecha_v10(21e170a9ba68) dimension: 64, alpha: 64.0, multiplier_unet: 0.3, multiplier_tenc: 0.3 create LoRA for Text Encoder: 72 modules. create LoRA for U-Net:...

``` error: output type 'tensor' and mean type 'tensor' are not broadcast compatible ``` On a mac tiledVAE does not work while MultiDiffusion does
Can this be used for upscaling instead of HighRes Fix or can upscaling only be done img2img?
I recently just installed the plugin, so I apologize if I did anything wrong. Essentially, when I try to use MultiDiffusion alongside ControlNet, I receive an error. MultiDiffusion's settings were...
MultiDiffusion Seems to be doing worse (not sharp) or am i doing something wrong? original:  MultiDiffusion:  Ultimate SD Upscale: 
I cannot get good results with this in i2i upscaling. Outputs are decent, but seemingly not better than ultimate SD upscale. Can you give some example settings for upscaling? And...
Sorry but when I try them in t2i or i2i (defalut settings),it always report" RuntimeError: Cannot set version_counter for inference tensor", is any mistake I have made ? I haven't...
Please forgive me for my poor English. When I use (mult) and (vav), I use the default, but the rendered image still repeats two people, write(1 girl) in the tag....