AsyncDiff

AsyncDiff copied to clipboard

pipe for img2img

1

Thank for your repo,Can this method be used on img2img, such like diffusers/stable-diffusion-xl-1.0-inpainting-0.1?Looking forward to your reply,thanks!

Hxd1995

Hi, currently the difussion isn't the bottleneck, it's more the fact that I repeat the same process for each frame and the process invoke multiple part (like depth estimation, text...

softyoda

Clarification Needed on Diffusion Process

2

Hi authors, Thank you for your fascinating paper. However, I have a question regarding the diffusion process as illustrated in Figure 3 (https://github.com/czg1225/AsyncDiff/blob/main/assets/fig2.png?raw=true). From the image and the paper, it...

fairchildfzc

splite_mode, pipe_id for "RunDiffusion/Juggernaut-X-v10"

4

ChuRuaNh0

Does it only support multiple devices and not support acceleration for a single device? I reported an error when using Colab in Controlnet and IP adapter

1

AssertionError Traceback (most recent call last) [](https://localhost:8080/#) in () 19 20 control_image.save("control.png") ---> 21 async_diff = AsyncDiff(pipe, model_n=2, stride=1, time_shift=False) 22 23 async_diff.reset_state(warm_up=1) [/content/AsyncDiff/src/async_sd.py](https://localhost:8080/#) in __init__(self, pipeline, model_n, stride, warm_up,...

libai-lab

about FLUX.1

1

Do you have plans to support FLUX.1?

echosyy

MeiYi-dev