search

light-and-ray / sd-webui-replacer

A tab for sd-webui for replacing objects in pictures or videos using detection prompt
208 stars 11 forks source link

The problem of the image being black after the clothes are redrawn has always existed. What caused this, #73

Closed fengyunwuji728 closed 6 months ago

fengyunwuji728 commented 6 months ago

The problem of the image being black after the clothes are redrawn has always existed. What caused this, QQ截图20240515193805 258

[

https://github.com/light-and-ray/sd-webui-replacer/assets/22515039/7177d1ce-61a3-4345-87f8-b6ef29a541eb

](url)

light-and-ray commented 6 months ago

Does it is in single image mode (also with controlnet inpainting module on)? Send your full console log, and which other extensions you use

fengyunwuji728 commented 6 months ago

Not single image mode, single image is normal, and multiple images are also normal. I am using video, but the video is not normal

light-and-ray commented 6 months ago

Please send me your full console log

fengyunwuji728 commented 6 months ago

1 2 3 4 5 6

fengyunwuji728 commented 6 months ago

8

fengyunwuji728 commented 6 months ago

Error running before_process_batch: F:\ai\sd-webui-aki-v4.7\extensions\sd-webui-animatediff\scripts\animatediff.py Traceback (most recent call last): File "F:\ai\sd-webui-aki-v4.7\modules\scripts.py", line 833, in before_process_batch script.before_process_batch(p, script_args, kwargs) File "F:\ai\sd-webui-aki-v4.7\extensions\sd-webui-animatediff\scripts\animatediff.py", line 79, in before_process_batch AnimateDiffI2VLatent().randomize(p, params) File "F:\ai\sd-webui-aki-v4.7\extensions\sd-webui-animatediff\scripts\animatediff_latent.py", line 84, in randomize p.init_latent = p.init_latent init_alpha + p.rng.next() (1 - init_alpha) RuntimeError: The size of tensor a (12) must match the size of tensor b (5) at non-singleton dimension 0

fengyunwuji728 commented 6 months ago

After turning off semi precision optimization, it went back to normal