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
Is it possible to customize the UI for forge ? Like adding brand logo, rearranging features
Not to delete any existing features, just to rearrange them so that the whole visual look is less complex and has personal visual taste @Furkan Gözükara SECourses
Hey everyone! I've had mixed experiences with different Flux models and I'd like to share my findings and ask for help:
Successfully trained a LoRA using flux1-dev.safetensors with Dreambooth following the tutorial video. The results were excellent - I can generate both realistic and stylized images with great quality. However, the pose control with this model is quite poor.
When Flux tools were released, I was excited but encountered two issues:
When I try to use my previously trained safetensors (trained with flux1-dev) with the Flux tools, it doesn't work well - generates very poor quality images.
So I tried training a new Dreambooth LoRA using flux1-canny-dev.safetensors, but got this error:RuntimeError: Error(s) in loading state_dict for Flux:size mismatch for img_in.weight: copying a param with shape torch.Size([3072, 128]) from checkpoint, the shape in current model is torch.Size([3072, 64]).
Has anyone successfully trained a Dreambooth LoRA with flux1-canny-dev.safetensors? If so, could you share your setup/approach?
I really want to combine the quality I achieved with flux1-dev with proper pose control from the new Flux tools.
I have achieved much better results when using these resolutions. Often you can miss the point of the image if you crop it and use 1024x1024. But it is very important that if you use a size that is not 1024x1024 you crop at least 8 images to that size.
I was able to get a pretty good result with a Flux LoRA I trained last month with two unique characters. But maybe the AI has has an easier time telling them apart when they're different genders. The dataset containing images with them posing next to each other maybe helped too
Guys, getting this error when trying a pony checkpoint in swarmui: "ComfyUI execution error: Given groups=1, weight of size [512, 16, 3, 3], expected input[1, 4, 144, 112] to have 16 channels, but got 4 channels instead" any idea how to fix this?
I been working on the same picture all morning and can't get it to do it-- I've used various workflows and what not; other models will work with the same workflows (but not the same effect)--
Just now, I finally tried another image; and said cow with a guidance on 30, and well it worked except it gave me a man, not a cow-- so I am really confused--