Fangfang Chen comments

Results 7 comments of


                                            Fangfang Chen

[Scribble] How to catch the color in input image?

Maybe you can try multi-control with controlnet_scribble + t2i_color in the webui

[Scribble] How to catch the color in input image?

@lxxie298 I later tried another method, using the color map as input for img2img (with around 0.9 denoising weight), which could also achieve a similar effect. I hope it will...

Question about params_emb

Thank you! Actually I meet the error when run the code: RuntimeError: The expanded size of the tensor (99) must match the existing size (100) at non-singleton dimension 0 And,...

Question about params_emb

OK, Thank you!

Why I always meet the error "requests.exceptions.SSLError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /openai/clip-vit-large-patch14/resolve/main/vocab.json (Caused by SSLError(SSLError("bad handshake: SysCallError(104, 'ECONNRESET')")))"

yes, you should download the model file locally in advance ---- Replied Message ---- | From | ***@***.***> | | Date | 12/22/2023 09:45 | | To | ***@***.***> |...

Why is the drawing efficiency very slow after using controlnet? I use a 4090 graphics card, use image2image, 720P, and it takes an average of 7-8 seconds for a picture, and an average of 2~3it/s. I use 3 controlnets to superimpose, Is there any way to speed it up?

I use Tesla V100, also made 7~8 second per case.

请问如何复现resnet50模型的结果？

input目录下分为train, valid, test文件夹，其中train和valid目录下是一系列按class组织的目录，如0, 1, 2...79，每个目录中存放对应class的图片。