![NewGenAI](/img/default-banner.jpg)
- 52
- 33 323
NewGenAI
India
Registrace 5. 01. 2024
đ Welcome to StableAIHub - Your Gateway to AI Innovation! đ€âš Dive into the forefront of artificial intelligence and explore the fascinating world of Stable Diffusion with us. Uncover the magic where stability meets creativity, as we unravel the secrets of generating stunning images from text prompts. Whether you're an AI enthusiast, a tech explorer, or a creative mind seeking inspiration, you're in the right place. Join our community, stay updated on the latest breakthroughs, and embark on a journey of discovery in the ever-evolving landscape of AI. Subscribe now and let's shape the future together! đđ #StableDiffusion #AIInnovation #TechExploration
Ultimate Vocal Remover: Effortless Vocal Extraction with Deep Neural Networks
github.com/Anjok07/ultimatevocalremovergui
#AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #UltimateVocalRemover #AudioEditing #MusicProduction #VocalRemover #DeepLearning #Karaoke #MusicTools #SourceSeparation
#AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #UltimateVocalRemover #AudioEditing #MusicProduction #VocalRemover #DeepLearning #Karaoke #MusicTools #SourceSeparation
zhlĂ©dnutĂ: 38
Video
Make Backgrounds Disappear: Quick and Easy Transparent Background Tool | Powered by InSPyReNet
zhlĂ©dnutĂ 71PĆed 16 hodinami
Readme / Instructions drive.google.com/file/d/1xME6LJUN7lYd9fDh1-xBLSZ8Y5ilr1w8/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #TransparentBackground #BackgroundRemoval #InSPyReNet #ImageEditing #VideoEditing #P...
AICoverGen: Create Song Covers with RVC v2 AI Voices!
zhlĂ©dnutĂ 129PĆed 18 hodinami
Readme / Instructions drive.google.com/file/d/1r2zuruBUJwbox30N1BTp2s6sicqSZlac/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #AICoverGen #AISongCovers #RVCv2Voices #AIVoiceSynthesis #AIMusic #AISinging #AIAssi...
EchoMimic Magic: Audio and Landmarks Bring Portraits to Life!
zhlĂ©dnutĂ 1KPĆed 14 dny
Readme / Instructions drive.google.com/file/d/1YjxU3QVF7EaL6hFd9uQqJxovMMX-SuKJ/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #EchoMimic #audiotovideo #lipsync
How to Create Perfect Lipsync Videos with LipSick
zhlĂ©dnutĂ 268PĆed 14 dny
Readme / Instructions drive.google.com/file/d/1l9C4Nd-H1D_cbGaVF-_XKz-WgaZb-e4H/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #LipSick #audiotovideo #lipsync
FSRT: AI-Powered Next-Gen Face Reenactment Technology
zhlĂ©dnutĂ 333PĆed 21 dnem
Readme / Instructions drive.google.com/file/d/1wbLsh7fDw-yg39w_rthKMTMJ4eq7gZkc/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #FSRT #funnyvideo #funnyexpressionvideos #facereenactment
LivePortrait: Create Hilarious Portrait Animations Effortlessly!
zhlĂ©dnutĂ 2,7KPĆed 21 dnem
Updated the video to align with the updates released couple of hours back Thanks to @Rene_Requiestas for informing about the changes Readme / Instructions drive.google.com/file/d/1PQc2hegZtTXGBUXsl2ndtOv4vo23iokC/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #Tec...
MimicMotion: Revolutionizing Human Motion Videos
zhlĂ©dnutĂ 1,4KPĆed 21 dnem
Readme / Instructions drive.google.com/file/d/1_dV2Nk9eHqQqz-2vHlIXKj1y3d8myw7B/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #MimicMotion #humanmotion #dancingvideos #aidancingvideo
Hallo: Breakthrough in Audio-Driven Portrait Animation
zhlĂ©dnutĂ 674PĆed 21 dnem
Readme / Instructions drive.google.com/file/d/1lZpXPHqt6Xvp339j9E7ruiayJCYkO4Wb/view?usp=sharing #AI #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #Hallo #talkinghead #talkingheadvideo #talkingheads Credits for Quack Quack audio in...
FaceSwapLab for Stable Diffusion: Seamless Face-Swapping in Automatic1111
zhlĂ©dnutĂ 648PĆed 28 dny
FaceSwapLab github.com/glucauze/sd-webui-faceswaplab Installation steps drive.google.com/file/d/15Q4Vi7OSopl4itS_s3aF7gmkkbWgKLqa/view?usp=sharing #ai #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthroughs #AIResearch #futuristictechnology #faceswapai #faceswapping #faceree...
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion
zhlĂ©dnutĂ 447PĆed 28 dny
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models github.com/yl4579/StyleTTS2 Installation steps drive.google.com/file/d/1VyyVJfGaFmcURw3zDnzYDhMZTwXp8DaF/view?usp=sharing #ai #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommuni...
Face-Adapter: The Ultimate Tool for Perfect Face Reenactment & Swapping
zhlĂ©dnutĂ 367PĆed mÄsĂcem
Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control github.com/FaceAdapter/Face-Adapter Installation steps drive.google.com/file/d/1quWcNYRm8Up16WG_A0l6Mnlsyk15gE_8/view?usp=sharing #ai #StableDiffusion #TechInnovation #ArtificialIntelligence #DeepLearning #AIExploration #TechEnthusiast #CreativityInAI #StableAIHub #AICommunity #InnovationHub #TechBreakthrou...
Transforming Images into Lifelike Conversations: V-Express installation & demo on windows 11
zhlĂ©dnutĂ 367PĆed mÄsĂcem
Transforming Images into Lifelike Conversations: V-Express installation & demo on windows 11
Stable Diffusion 3 Medium: The Future of AI Art is Here! Installation and quick demo on Windows 11
zhlĂ©dnutĂ 862PĆed mÄsĂcem
Stable Diffusion 3 Medium: The Future of AI Art is Here! Installation and quick demo on Windows 11
Boost Image Diversity: Discover CADS for Automatic1111 WebUI
zhlĂ©dnutĂ 154PĆed mÄsĂcem
Boost Image Diversity: Discover CADS for Automatic1111 WebUI
Revolutionize Dance Videos with MusePose: The Ultimate Virtual Human Generator!
zhlĂ©dnutĂ 1,8KPĆed 2 mÄsĂci
Revolutionize Dance Videos with MusePose: The Ultimate Virtual Human Generator!
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
zhlĂ©dnutĂ 395PĆed 2 mÄsĂci
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
QualityScaler: Your Ultimate Photo and Video Enhancement Solution
zhlĂ©dnutĂ 361PĆed 2 mÄsĂci
QualityScaler: Your Ultimate Photo and Video Enhancement Solution
Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
zhlĂ©dnutĂ 377PĆed 2 mÄsĂci
Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
IDM-VTON: Redefining Virtual Try-On Experiences
zhlĂ©dnutĂ 1,7KPĆed 2 mÄsĂci
IDM-VTON: Redefining Virtual Try-On Experiences
Now change Hair, Face, Background, Clothes using Auto-Mask in A1111 like a Pro
zhlĂ©dnutĂ 556PĆed 3 mÄsĂci
Now change Hair, Face, Background, Clothes using Auto-Mask in A1111 like a Pro
[use case] Colorized "Ye dil aur unki nigahon ke saaye" black-and-white era song using Deoldify extn
zhlĂ©dnutĂ 660PĆed 3 mÄsĂci
[use case] Colorized "Ye dil aur unki nigahon ke saaye" black-and-white era song using Deoldify extn
Bring Your Old Memories to Life with Deoldify on AUTOMATIC1111
zhlĂ©dnutĂ 241PĆed 3 mÄsĂci
Bring Your Old Memories to Life with Deoldify on AUTOMATIC1111
Add delete button in Automatic1111 WebUI
zhlĂ©dnutĂ 201PĆed 3 mÄsĂci
Add delete button in Automatic1111 WebUI
Stable Video Diffusion SV3D Unveiled: Transform Images into Dynamic 3D Videos
zhlĂ©dnutĂ 285PĆed 3 mÄsĂci
Stable Video Diffusion SV3D Unveiled: Transform Images into Dynamic 3D Videos
Tech Tips: Remove the background from camera in OBS Studio - Windows 11
zhlĂ©dnutĂ 115PĆed 3 mÄsĂci
Tech Tips: Remove the background from camera in OBS Studio - Windows 11
Bring old Photos Back to Life using Automatic1111 and Old Photo Restoration extension
zhlĂ©dnutĂ 871PĆed 3 mÄsĂci
Bring old Photos Back to Life using Automatic1111 and Old Photo Restoration extension
Pro Tips: Unlocking Seamless Updates in Automatic1111
zhlĂ©dnutĂ 134PĆed 3 mÄsĂci
Pro Tips: Unlocking Seamless Updates in Automatic1111
Pro Tips: Multiple Checkpoint with X/Y/Z Plot Script in Automatic1111 using X plot
zhlĂ©dnutĂ 105PĆed 3 mÄsĂci
Pro Tips: Multiple Checkpoint with X/Y/Z Plot Script in Automatic1111 using X plot
Pro Tips: Unlocking Clip Skip & VAE Selector in Automatic1111 WebUI
zhlĂ©dnutĂ 974PĆed 3 mÄsĂci
Pro Tips: Unlocking Clip Skip & VAE Selector in Automatic1111 WebUI
Issue with No Sound Output
There could be new updates recently. Please merge the audio using any video editing tool.
Thank you very much for your videos, you explain all the steps clearly, keep it up!
Thanks for your feedback
Love it
Lol. How do you create these?
It's funny.
Thank you for these easy guides.
I gave up months ago on trying to install this tool. Thank you for compiling an easy guide. It is working fine.
I also gave up but after a lot of tries it worked. I thought it will be helpful for the community.
This is really useful. Thank you
Glad to know it was useful.
Traceback (most recent call last): File "webgui.py", line 70, in <module> vae = AutoencoderKL.from_pretrained(config.pretrained_vae_path).to("cuda", dtype=weight_dtype) File "/opt/anaconda3/envs/echomimic/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1152, in to return self._apply(convert) File "/opt/anaconda3/envs/echomimic/lib/python3.8/site-packages/torch/nn/modules/module.py", line 802, in _apply module._apply(fn) File "/opt/anaconda3/envs/echomimic/lib/python3.8/site-packages/torch/nn/modules/module.py", line 802, in _apply module._apply(fn) File "/opt/anaconda3/envs/echomimic/lib/python3.8/site-packages/torch/nn/modules/module.py", line 825, in _apply param_applied = fn(param) File "/opt/anaconda3/envs/echomimic/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1150, in convert return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking) File "/opt/anaconda3/envs/echomimic/lib/python3.8/site-packages/torch/cuda/__init__.py", line 293, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled")
how did this really work in your case? because in the git page they say to create a ModelScope/t2v folders and put there the following: VQGAN_autoencoder.pth configuration.json open_clip_pytorch_model.bin text2video_pytorch_model.pth
There may be some updates after this video was created. Please follow the instruction as mentioned in github page.
The quallity of the accelerated version is not good. I will just use the slower version for now
I noticed the same. Used the slower version for next video. Did you came across any tool for singing talking head.
@@StableAIHub next release of echomimic would have Pretrained models with better sing performance to be released
Nice đ how to create AI generated image to sing
Let me see if I find anything which is open source. There are quite few but are paid and can't be installed locally.
@@StableAIHub thanks âșïž
Is the new update working? Im having lots of errors
A2V with acceleration is working fine. Please could you share error screen using Drive.
@@StableAIHub Thanks its working fine now. The Gradio is the one that is not working
@@Rene_Requiestas If no one is gonna fix I will see if I can. I am not a programmer so gonna take help from AI. By any chance do you have the old version / earlier release of EchoMimic when it was working
@@Rene_Requiestas Please check the github, I posted the solution. If you can confirm on github, it can be merged in repo
@@StableAIHub i made a mistake by cloning the latest version and copy paste it to the original/old. I no longer have the old working version
Thanks, can we run this google colab or in cloud
I could not find any collab version. You can try other lip sync tools posted in this channel
Great
Another interesting list: harlanhong/awesome-talking-head-generation
Sir i getting this error. Error occurred when executing DownloadAndLoadMimicMotionModel: Error no file named config.json found in directory C:\Users\akash\Documents\ComfyUI_windows_portable\ComfyUI\models\diffusers\stable-video-diffusion-img2vid-xt-1-
This is a standalone installation tutorial. I don't use ComfyUI so not sure about how to install in Comfyui.
so interesting
hello, can you help me? im getting this error, i tried all! cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
Please join Discord and read the FAQ. There are solutions provided. discord.com/channels/1129031320148918292/1190309613594230874
@@StableAIHub thanks, sorry the link wont take me to a discord channel! can you please send it again?
@@AlasVic discord.gg/ajzA9NVZCc
How to create image vexel art with a1111
What is it that you want to create, some examples please. As I understand it is to do with finding the right pre-trained model.
See if this helps civitai.com/tag/vector%20art
Her nose still has black and white after render, which is not colorized by this tool
Can't expect perfect output but does pretty good job. I tried here czcams.com/video/io82Dmy8y1U/video.html
I just wanna say thank you for your tutorials. great job
Thank you for your feedback
Hi again, after watching this mutiple times i am wondering what is difference btwn step 1 git clone and step 7 git clone because its the same idm vton from same creator. (1 from github and 7 from huggingF.)
Step 1 is to clone the code and Step 7 is to clone pre-trained models.
I found this in github and seems interesting Kedreamix/Awesome-Talking-Head-Synthesis
Interesting collection, thanks for sharing. Will check if any of them can be installed on Windows. Did you tried FasterLivePortrait. I can't get it to work :(
Somehow I didn't get the notification for this comment.
@@StableAIHub i tried but i dont know anything about docker
I have posted in the issue section. I hope it works.
Great! thanks a lot! subbed!
Awesome, thank you!
Hi. Is it possible to batch process a few images in code ?
It should be possible. I am busy this week so if you remind me on Saturday I will try and see how it can be done. You can also post in SadTalker github issue section.
@@StableAIHub Thanks I have posted there as well
hi this has come up in another youtubers video but is it necessary to use conda to create virtual environment's ? From all your videos i learned that we can create a venv on our own. So will this tutorial work if we don't use conda ? Thanks, b
The answer is long. Primarily we are using either PIP or CONDA to create virtual environment (VE). Sometimes the dependencies are very specific like some packages, python version... etc which can be easily done using conda. I don't know if this will work without conda. You need to try and let us know plz.
@@StableAIHub Got it. thanks for the info. Cheers, b
BAT file for launching @echo off REM Change to the directory of the batch file cd /d "%~dp0" REM Activate the EchoMimic environment call conda activate echomimic REM Launch WebUI python webgui.py --server_port=3000
Hi there, I tried ton install it for ComfyUI, but could not do so successfully (via Manager + copy paste all missing files from the repo). Could you please make a tutorial for ComfyUI please? đ
@@IdgrafixCh I am sorry, Comfy is not my cup of tea. It is a standalone install why use Comfyi. Comfy will occupy VRAM for it's own use and then this tool. Standalone means more VRAM available. That's my understanding.
OMG ! Is the OpenAI ROBOT now Dancing SALSA too ? đ¶ đ” OpenAI my Sugar Papi, by PEACHY da WHUUPi on CZcams, Insta,Spotify . HILARIOUS. CAN YOU GUESS WHICH A.I. I used ?
Good tool, better than HALLO which takes longer time to process. BTW, I created a bat file to start the program easier and faster.
can you share the bat file?
@@Rene_Requiestas The video publisher added the code for bat file and pinned it, you can copy and paste it in a text file, then change the extension to "bat".
@@TomiTom1234 thx
@@Rene_Requiestas You are welcome. Don't forget to change the paths that need to be changed to match your folders.
đGonna test this one out
I checked a bunch of videos on CZcams, but I failed to install LivePortrait every time, but you were perfect. Thank you.
Thank you so much for your kind words!
Is it work without nvidia gpu.
I think it may not work without GPU but no harm in trying. Try to install and see if it works
This AI is just the best out there in terms of quality compared to all others (Hedra, Liveportrait, Sadtalker, Hallo, V-express). It might be the right time to start saving for RTX 5090
Ha ha ha. True that, let me also start saving. Please could you check the teeth part. Are you happy?
I think eye blinking needs some improvement. Sometime only 1 eye blink.
@@StableAIHub Minor imperfections are ok. It's easy to edit in capcut by applying some effects. What is important for me is the skin texture similar to sadtalker.
@@Rene_Requiestas Right. The quality is good. I wasn't expecting this good for AI.
Thank you for the video, unfortunately I think the big roadblock with a lot of these talking head software is optimization, it took 17 minutes for a 5 second video, imagine if you had a 3 minute video, it would take 6hrs and 12 minutes which is just not a good use of your time, hopefully in the neat future they get better
The processing time can be significantly reduced if you use a 16GB or 24GB VRAM card. Using cloud services can further decrease the rendering time. A few months ago, the major issue was the quality, as the output would get distorted when using realistic images generated with SD. EchoMimic has surprised me with its improvements. I'm happy to see that the quality is getting better, and in due time, the speed will also improve. Unfortunately, I have the most basic laptop that only meets the minimum requirements, which explains the slow speed.
@@StableAIHub I think you'll agree, prices being what they are, most people either have a 12 or 8 gb and I think that is where the optimization focus should be:)
I agree what you said. I hope in due time the processing would be much faster on low VRAM cards.
@@StableAIHub i think devs plan to release a faster version of this in 1 to 2 months
I get a error. They say "ffprobe" not found. Whats is the problem?
Give me some time, I will post another tutorial. There were some updates which broke the code.
@@StableAIHub i found the Solution thanks. It is possible that works faster. It takes very long time.
It all depends on the hardware, primarily how much VRAM is available for processing.
bro, in all the trianing ive done the styletts2 model still sounds like a default AI. i only trained the pitch extractor and ASR differently but the model sound barely sounded differently than the prototype
Unfortunately I have never tried training the models as I do not have sufficient resources (VRAM). I suggest you post on their github page
Iâm at an aw of the consistency.. even if itâs not perfect now .. 2 papers down the line .. will be đ€Ż
I've had some issues, but it's a very easy and accurate guide. Thank you. How do I get this up and running on comfyui?
Not sure about ComfyUI, I don't use it. Post in the github issue section and someone might help you.
Just a general question. My SadTalker uses my CPU and it takes a long time. Is there a way to get SadTalker to use the GPU?
Several users faced this problem without solution. I posted another video related to SadTalker advanced features, try if that approach works. I would suggest post an issue on their GitHub page. You can also refer other tools for Lip Sync and see if that helps.
THANK YOU!!! I have been trying for 2 weeks to get SadTalker to run. I have had no luck on any vids that I watched. I ran across this one and noticed that you were doing things a little different than the others. SadTalker works flawlessly!!! You have a new subscriber now!
Good to know you got it working.
Bro, can you please make video on how to train Style tts model. i didn't understand google colab finetune training. its little bit confusing.
I am not sure about training part will but try.
If you get Access denied error, please refer this. Make sure video does not have missing face in any frame. github.com/Inferencer/LipSick/issues/21#issuecomment-2135802103 I mistakenly mentioned in video that it is related to missing package.
thank you so much After closing, how do I open it again? If possible, please provide detailed instructions
It is there in video Step 8: Run WebUI .\venv\Scripts\activate python app.py Watch video from here czcams.com/video/bRHf2oQwgG4/video.html
thank you sir. I am trying to run it in runpod with cloud storage and gpu. Do i have to install the same like you did for my set up?
I am not sure as I have never used RunPod. Please try to search tutorials for RunPod.
Hi Bro Can you help me with these errors please?
What error did you got. Please post errors
@@StableAIHub It doesn't allow me to add the error, can I send it to you by another means?
drive.google.com/file/d/1YapVqEfsdBEsTcyYwjmqcNCPsO4wSCwy/view?usp=drivesdk
Try this after activating virtual environment pip install setuptools
thank you so much. your tutorial is the only one that worked for me. keep up the great work đȘ
Good to know it was helpful. đ
BadToBest/EchoMimic
Thank you. Let me have a look
There is something similar called EchoMimic
Please could you share the link. I searched Google and Github but could not find anything
@@StableAIHub /BadToBest/EchoMimic
cartoon animator is dead.. ALL Animation software are dead now..
Not yet but yes in couple of years we will see near perfect output