G-force78

Disable duckduckgo privacy essentials beforehand

> manually download the checkpoints may works better, we give a new tutorial here: https://github.com/Winfredy/SadTalker/blob/main/docs/webui_extension.md Hi, where to put this file? s3fd-619a316812.pth https://drive.google.com/file/d/1EwGG1bS0EQA_R6yGoWm9BJVzli-erVpG/view?usp=sharing

Ok thanks for quick reply! Ive downloaded all the files in the gdrive and from the hub , do I need to the files from BFM_fitting too?

Try loading the latents of your best samples with fixed seed and settings

> Does it say anything in the console? No there was nothing anywhere, the UI kept running but nothing was produced. I did get it running later but the result...

import yaml from yaml import safe_load def load_checkpoints(config_path, checkpoint_path, cpu=False): with open(config_path) as f: config = yaml.load(f, Loader=yaml.SafeLoader)

Beyond me that I think! Is there a way to use your version in the collab drive I haven't room in my gdrive?

Same as prevuious commenter when running collab ``` Traceback (most recent call last): File "/content/stable-diffusion-webui/modules/scripts.py", line 195, in load_scripts module = script_loading.load_module(scriptfile.path) File "/content/stable-diffusion-webui/modules/script_loading.py", line 13, in load_module exec(compiled, module.__dict__)...

What is a good way to check if the results have been trained with good (enough) parameters? So far the likeness is hit and miss, usually miss, thats on 5...

Ah right I see, just change the path here? monkeypatch_lora(pipe.unet, torch.load(os.path.join(OUTPUT_DIR, "lora_weight.pt")))