T2I-Adapter
T2I-Adapter copied to clipboard
TencentARC
T2I-Adapter
Thanks to your great work！ But I can't understand some description in Section 3.3 Adapter Architecture.  1.dose the F_s here means F_c? 2.could you please explain the meaning and...
In the readme, you mentioned that we need to download the weights of CLIP, but isn't it included in the SD v1.4 checkpoint?
Why are the UNet parameters frozen during training for SD1v5, but not for SDXL? the haggingface training sdxl script sets " Unet.train() " ***** huggingface train sdxl ********* vae.requires_grad_(False) text_encoder_one.requires_grad_(False)...
There's a typo in the README where "varient" should be "variant".
Hi, The author mentioned, "The corresponding sketch maps are generated with the edge prediction model of [41] and then are thresholded with 0.5." in the main paper. I wanna know...
Hello,Thank you very much for your open-source work. I have a question regarding the visualization of the loss generated while running train_sketch.py. Below is the visualization of the validation loss....
From the openpose examples it looks like all the conditioning images have their red and blue channels swapped. Also it seems like the model behaves much better if you flip...
Hello! Thanks for the amazing project. I'm often in the situation where I've generated a scene I really like, but I'd like to rotate the camera a bit more to...
