르세라핌 티쳐영상이 짧고 어? 해볼만 한데 하고 덤볐는데 딱 작업 중간에 멈춰버리네..
이거 해결방법이 없을까용? 다른 짧은 영상도 비슷하게 멈추던데 왜이러는지 모르겠음
Error completing request████████████████████████▊ | 2516/5236 [3:20:36<3:32:36, 4.69s/it]
Arguments: ('task(1dxlxuy2yifptit)', 'RAW, masterpiece, best quality, ultra detailed, realistic, high resolution, high definition, finely detailed, vivid, photo realistic, kpop idol, beautiful girl, pretty face, detailed face, detailed eyes,Huge chest,huge pelvis,Full body ,best lighting,(8k, RAW photo, best quality, masterpiece:1.2), (realistic, photo-realistic:1.37, <lora:facebombmix_v1Bakedvae:1>', '(worst quality:1.6), (low quality:1.6), lowres, nsfw, torn clothes, EasyNegative, badhandv4, strabismus, crossed eyes, nude, nsfw,six fingers,bag, sack,Four arms,((((Three arms)))),((((furniture)))', 'C:\\Users\\user\\AppData\\Local\\Temp\\11a360b2fba3d135217f41c9a757bf2c3cf2790d\\새로운 프로젝트.mp4', 30, 16, False, False, False, None, None, 'none', 0, 0, 30, 1, 1, 7, 1.5, 0.56, 30, -1.0, -1.0, -1.0, 0, 0, 0, False, 1080, 1920, 0, [], 0, False, '', 0, <scripts.external_code.ControlNetUnit object at 0x000001CF15477970>, '<ul>\n<li><code>CFG Scale</code> should be 2 or lower.</li>\n</ul>\n', True, True, '', '', True, 50, True, 1, 0, False, 4, 0.5, 'Linear', 'None', '<p style="margin-bottom:0.75em">Recommended settings: Sampling Steps: 80-100, Sampler: Euler a, Denoising strength: 0.8</p>', 128, 8, ['left', 'right', 'up', 'down'], 1, 0.05, 128, 4, 0, ['left', 'right', 'up', 'down'], False, False, 'positive', 'comma', 0, False, False, '', '<p style="margin-bottom:0.75em">Will upscale the image by the selected scale factor; use width and height sliders to set tile size</p>', 64, 0, 2, 1, '', 0, '', 0, '', True, False, False, False, 0, False, False, False, '#000000', False, '<p style="margin-bottom:0.75em">Recommended settings: Use from inpaint tab, inpaint at full res ON, denoise <0.5</p>', 'None', 30, 4, 0, 0, False, 'None', '<br>', 'None', 30, 4, 0, 0, 4, 0.4, True, 32, 7, None, False, 50) {}
Traceback (most recent call last):
File "D:\sd.webui\webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "D:\sd.webui\webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "D:\sd.webui\webui\extensions\sd-webui-mov2mov\scripts\mov2mov.py", line 235, in mov2mov
generate_video = process_mov2mov(p, mov_file, movie_frames, max_frames, resize_mode, width, height,
File "D:\sd.webui\webui\extensions\sd-webui-mov2mov\scripts\mov2mov.py", line 93, in process_mov2mov
processed = process_images(p)
File "D:\sd.webui\webui\modules\processing.py", line 503, in process_images
res = process_images_inner(p)
File "D:\sd.webui\webui\modules\processing.py", line 657, in process_images_inner
devices.test_for_nans(x, "vae")
File "D:\sd.webui\webui\modules\devices.py", line 152, in test_for_nans
raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in VAE. This could be because there's not enough precision to represent the picture. Try adding --no-half-vae commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
Traceback (most recent call last):
File "D:\sd.webui\system\python\lib\site-packages\gradio\routes.py", line 394, in run_predict
output = await app.get_blocks().process_api(
File "D:\sd.webui\system\python\lib\site-packages\gradio\blocks.py", line 1078, in process_api
data = self.postprocess_data(fn_index, result["prediction"], state)
File "D:\sd.webui\system\python\lib\site-packages\gradio\blocks.py", line 1012, in postprocess_data
prediction_value = block.postprocess(prediction_value)
File "D:\sd.webui\system\python\lib\site-packages\gradio\components.py", line 1991, in postprocess
y = self.make_temp_copy_if_needed(y)
File "D:\sd.webui\system\python\lib\site-packages\gradio\processing_utils.py", line 362, in make_temp_copy_if_needed
temp_dir = self.hash_file(file_path)
File "D:\sd.webui\system\python\lib\site-packages\gradio\processing_utils.py", line 334, in hash_file
with open(file_path, "rb") as f:
FileNotFoundError: [Errno 2] No such file or directory: '