T2I-Adapter

T2I-Adapter copied to clipboard

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

3


qingfengmingyue

@MC-E Hey! First of all thanks for a very interesting paper, I like your approach more than CN, due to it being much faster. Looking Figure 5. in your paper...

bonlime

Hi, I was wondering if i can use Mediapipe holistics ( which includes 543 whole body keypoints) to the T2I-Adapter or not? I saw that openpose, MMPose keypoints can be...

p0mad

Can T2I-Adapter be used for SD-2.x？

5

I wonder whether T2I-Adapter could be used for SD-2.x ?

rnwang04

whydna

[Warning] ControlNet finds unexpected mis-alignment in tensor shape.

1

Whenever I use t2iadapter_color-fp16.safetensors I get this error: `[Warning] ControlNet finds unexpected mis-alignment in tensor shape.` Any thoughts what this might be or how to fix it? I'm running the...

evanerichards

如题, 当我用style或者color的时候, 生成的人物皮肤也是这种风格和颜色. .... 我想要做的是给一张图片用style或者color, 生成人物, 人物皮肤部分不变, 衣服还有其它用style或者color生成....

aaronkingdom

question about Non-uniform time step sampling during training

1

The paper mentions the use of Non-uniform time step sampling during training, but no relevant parameters are found in the training code. How can this strategy be applied?

westfish

style train

1

Hello! Thank you very much for this, it seems really good! I am wondering how the style adapter trained, for example, I have van Gogh images， then the input of...

Xiang-cd

About training document

2

Hello! Thank you very much for this, it seems really good! Could you provide some training documentation please? @MC-E

pokameng