DuroCuri comments

Repositories
Issues
Comments

Results 5 comments of


                                            DuroCuri

How many RAM needs to train model?

Maybe 24g ram is crucial.

Is there any method to segment more than 1 word caption in groundingdino?

> I have encountered the same problem. Is there a solution? Yes, its fixed. Modify node.py 233-235 in this way ![d38fa698afbd0b7850489273dc4e27d](https://github.com/storyicon/comfyui_segment_anything/assets/118010803/56acfd2d-ea24-4e8a-899c-7230f53b8473)

Suggestion: allow multiple prompts ("captions")

The same question, Please

How to resovle this problem? tips："Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work"

Sure, my default is the same. Did you solve it yet?

How to use locally downloaded models？

I got the same problem cause I download this flux model seperately with chrome. You should git lfs install all file of flux, thus is quarter than the single safetrensors....