多数二次元图片无法识别出面部

[w4xxx]

C:\Users\Hasee\AppData\Local\Temp\tmpgo2smyo_.png Traceback (most recent call last): File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\python\lib\site-packages\gradio\routes.py", line 394, in run_predict output = await app.get_blocks().process_api( File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\python\lib\site-packages\gradio\blocks.py", line 1075, in process_api result = await self.call_function( File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\python\lib\site-packages\gradio\blocks.py", line 884, in call_function prediction = await anyio.to_thread.run_sync( File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\python\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\python\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\python\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, args) File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui\modules\call_queue.py", line 15, in f res = func(args, **kwargs) File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui/extensions/SadTalker\src\gradio_demo.py", line 111, in test first_coeff_path, crop_pic_path, crop_info = self.preprocess_model.generate(pic_path, first_frame_dir, preprocess) File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui/extensions/SadTalker\src\utils\preprocess.py", line 94, in generate x_full_frames, crop, quad = self.croper.crop(x_full_frames, still=True, xsize=512) File "E:\aiPainter230121\stable-diffusion-webui_23-01-20\stable-diffusion-webui/extensions/SadTalker\src\utils\croper.py", line 170, in crop raise 'can not detect the landmark from source image' TypeError: exceptions must derive from BaseException

有什么办法吗？

[vinthony]

二次元图像需要单独的模型进行训练

[w4xxx]

二次元图像需要单独的模型进行训练 感谢大佬，看来只能等待新模型了。

[H9990HH969]

请问现在有二次元，或者是那种大头吉祥物的模型了吗？

[jelly-liu]

二次元图像需要单独的模型进行训练

i run vinthony/SadTalker on m1, 256256 work well, where i can get 512512 or higher 1024*1024 model, thank you so mush. @vinthony