Hello everyone. I am Dr. Furkan Gözükara. PhD Computer Engineer. SECourses is a dedicated YouTube channel for the following topics : Tech, AI, News, Science, Robotics, Singularity, ComfyUI, SwarmUI, ML, Artificial Intelligence, Humanoid Robots, Wan 2.2, FLUX, Krea, Qwen Image, VLMs, Stable Diffusion
with outpainting in all direction, or basically extending the crop. I am using fooocus and get this weirdness on some images where the image meets the outpaint area it extended from
does anyone have a tool or workflow to enhance image quality for blurry images, but not upscale? For example you took a bad picture with a mobile phone, and are looking to make it a hq picture. I have tried downscaling it manually and then upscaling it with SUPIR, which kinda works, but it's not really the intended use
An AI-upscaler should have understood that those were more like freckles than like floating leaves. I think SUPIR is good enough for this. This just seem to be same same but different
i think it depends what you expect from an upscaler : Just upscaling ? There are already dozens built in upscalers ion WebUI f.e which do a brilliant job. Enhancing an image ? Adding spice ? Well...maybe it's better to upscale and then inpaint again ?
but this discussion might be as old as models and extensions themself
Hey Every one, long time did not do a training lora of google collab, now i connected and a lot of things are outdated , anyone does have a legit link for IPYNB file please for kohya lora dreambooth ? thank you
I think that SUPIR AI isn't creative enough to add details as MAGNIFIC AI .. If someone knows how to use it on ai generated images to add much details for realism I would be thankful to him.
i have this error : ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. tf-keras 2.15.1 requires tensorflow<2.16,>=2.15, but you have tensorflow 2.16.1 which is incompatible. torchaudio 2.3.0+cu121 requires torch==2.3.0, but you have torch 2.1.0 which is incompatible. torchtext 0.18.0 requires torch>=2.3.0, but you have torch 2.1.0 which is incompatible.