Hello everyone. I am Dr. Furkan Gözükara. PhD Computer Engineer. SECourses is a dedicated YouTube channel for the following topics : Tech, AI, News, Science, Robotics, Singularity, ComfyUI, SwarmUI, ML, Artificial Intelligence, Humanoid Robots, Wan 2.2, FLUX, Krea, Qwen Image, VLMs, Stable Diffusion
magic animate seems to have a different color palette than the ones in the linked detectron repo also, or maybe it's just the fact the background is that shade of purple?
would need to also split a video into its images with ffmpeg in a previous step, then apply_net and then reassemble the output images it did looks like
I have installed and working. But there is literally 0 documentation and examples. in the same folder densepose_rcnn_R_101_FPN_DL_s1x.yaml located in the same folder Base-DensePose-RCNN-FPN.yaml lo...
Hello Furkan, DR. Siva replied the following to me: I am getting the same results , i was able to avoid by
check resolution 1024x1024 ( start with this res)
Decrease steps to 30
Use 2M karras sampler
Use some other models (ProtovisionXL,NightvisionXL) euler a does produce these, but it has to do with sampling step as well. in my case the last step creates these artificats. Also which lora output number are you using ? For me somewhere from 11-15 gives decent resuilts
The webui.zip is a binary distribution for people who can't install python and git. Everything is included - just double click run.bat to launch. No requirements apart from Windows 10. NVIDIA o...
im autist from euruope and i think this is sarcasm haha, but yes as a cs person programming shit is actually fucking difficult, like what the f is everything, i have no idea. docker, networkvolumes, gradio, api shit, errors browser. loool. pray for me. service layer.
wish my gpu was free right now, this seems promising and it has video input, maybe it does the apply_net step already since it mentions "show visualizations in an opecv window"
not sure if you went through that already however or if any of those models that are pretrained are the same one magic needs
3 days ago I was able to print 2048x2048 images with 4060 8gb vram, but now I can not print. If idle vram usage can help me in this case, thank you very much in advance. RuntimeError: Not enough memory, use lower resolution (max approx. 1600x1600). Need: 6.0GB free, Have:4.2GB free I'm dealing with this problem, do you know how to solve it.
The webui.zip is a binary distribution for people who can't install python and git. Everything is included - just double click run.bat to launch. No requirements apart from Windows 10. NVIDIA o...
apply_net definitely outputs what's needed for magic-animate, albeit with border and background image itself, doing it frame-by-frame would take ages this way however because it loads the model up on each invocation