![My AI Force](/img/default-banner.jpg)
- 24
- 125 012
My AI Force
United States
เข้าร่วมเมื่อ 6 ม.ค. 2024
Welcome to the future of art, a place where imagination meets AI!
Our channel is dedicated to demystifying the world of Stable Diffusion, Midjourney, and DALL-E through engaging tutorials.
Step into a realm where technology empowers your creativity, and every tutorial brings you closer to mastering the art of AI. Subscribe and paint your masterpiece with the brush of AI!
Our channel is dedicated to demystifying the world of Stable Diffusion, Midjourney, and DALL-E through engaging tutorials.
Step into a realm where technology empowers your creativity, and every tutorial brings you closer to mastering the art of AI. Subscribe and paint your masterpiece with the brush of AI!
ComfyUI Flux (ControlNet) Workflow: Replacing Background for Anything (Portrait, Product, etc.)
Welcome to the channel! In today's tutorial, we're diving into an exciting new technique for effortlessly changing photo backgrounds using ComfyUI and Flux models. Whether you're looking to enhance product shots, portraits, or any type of image, this step-by-step guide will show you how to create stunning transformations with ease.
Ready to transform your photos? Watch the full video now and follow along as I guide you through each step to create visually stunning images. Don’t forget to download the workflow link provided in the video description and start editing like a pro today!
👉 Hit play, and let's get started on this creative journey! Don’t forget to like, share, and subscribe for more tutorials like this.
🖹 Article Tutorial: myaiforce.com/flux-replace-background/
🔗 Download this workflow: openart.ai/workflows/myaiforce/UdbHePrLFEP9WzdrmmFj
🔗 Checkpoints:
- Flux fp8: huggingface.co/Kijai/flux-fp8
- epiCRealism: civitai.com/models/25694/epicrealism
- Juggernaut XL Lightning: civitai.com/models/133005?modelVersionId=357609
🔗Models:
- Flux ControlNet Canny V3: huggingface.co/XLabs-AI/flux-controlnet-canny-v3
📌 Chapters:
0:00 - Intro
1:15 - Overview of the Workflow
2:22 - Node Group 1: Background Removal
5:33 - Node Group 2: Background Generation
9:56 - Node Group 3: Relighting
11:32 - Node Group 4: Repainting
12:41 - Node Group 5: Detail Restoration
Ready to transform your photos? Watch the full video now and follow along as I guide you through each step to create visually stunning images. Don’t forget to download the workflow link provided in the video description and start editing like a pro today!
👉 Hit play, and let's get started on this creative journey! Don’t forget to like, share, and subscribe for more tutorials like this.
🖹 Article Tutorial: myaiforce.com/flux-replace-background/
🔗 Download this workflow: openart.ai/workflows/myaiforce/UdbHePrLFEP9WzdrmmFj
🔗 Checkpoints:
- Flux fp8: huggingface.co/Kijai/flux-fp8
- epiCRealism: civitai.com/models/25694/epicrealism
- Juggernaut XL Lightning: civitai.com/models/133005?modelVersionId=357609
🔗Models:
- Flux ControlNet Canny V3: huggingface.co/XLabs-AI/flux-controlnet-canny-v3
📌 Chapters:
0:00 - Intro
1:15 - Overview of the Workflow
2:22 - Node Group 1: Background Removal
5:33 - Node Group 2: Background Generation
9:56 - Node Group 3: Relighting
11:32 - Node Group 4: Repainting
12:41 - Node Group 5: Detail Restoration
มุมมอง: 2 418
วีดีโอ
Fix Plastic Skin for Flux (Workflow Included)
มุมมอง 2.1K14 วันที่ผ่านมา
Welcome to another insightful tutorial by Wei! In today's video, I’ll guide you through a comprehensive ComfyUI workflow designed to elevate the skin realism of portraits generated by the Flux models. If you’ve noticed that your Flux-generated portraits tend to have a plastic-like appearance, especially in the skin textures, this tutorial is tailor-made for you. What You’ll Learn: - Mastering F...
Flux Dev vs Midjourney V6.1 (Typography | Anatomy | Prompt Following | Hands | Face | Image Quality)
มุมมอง 41021 วันที่ผ่านมา
Welcome back, creators! My name is Wei. In today's video, we dive deep into the world of generative art by exploring the newly released open-source model suite, FLUX from Black Forest Labs. This suite is making headlines for allegedly outperforming even the most popular models like Midjourney, and today, we're putting that claim to the test. 🔍 Key Takeaways: - Text Generation & Typography: Disc...
Perfect Product Photography = Midjourney & ComfyUI | Workflow V2 Update
มุมมอง 1.1K28 วันที่ผ่านมา
Welcome to my channel! I'm Wei, and in today's tutorial, we're diving deep into how to create stunning product photography using MidJourney and my upgraded ComfyUI workflow. Whether you're looking to generate captivating product backgrounds or seamlessly integrate your own products into a scene, this video has got you covered. What You'll Learn: - How to generate custom product backgrounds usin...
ComfyUI Stunning Product Photography (Workflow included, customized placement & detail retention)
มุมมอง 2Kหลายเดือนก่อน
Hey everyone, my name is Wei, welcome to my channel! Today, I'm thrilled to share my latest project: a comprehensive tutorial on using ComfyUI for creating stunning product photography. Whether you're a beginner or an experienced designer, this workflow will help you blend products seamlessly into any background with ease. In this video, you will learn: - How to use ComfyUI to integrate a produ...
Use Stable Diffusion to Mimic Midjourney Style
มุมมอง 1.2K2 หลายเดือนก่อน
Welcome to my channel! In this video, I'll guide you through the process of making your Stable Diffusion-generated images resemble the stunning art styles of Midjourney. We'll explore various LoRAs and demonstrate how to combine them to achieve different artistic effects. What You'll Learn: - Combining LoRAs for Unique Styles: Discover how to use "Midjourney V6 Style," "Midjourney mimic," "xl_m...
Forget SD3 Medium: These Models Are Better!
มุมมอง 2.1K2 หลายเดือนก่อน
Hello everyone, my name is Wei and welcome to my channel! Today, we're diving into the newly open-sourced Stable Diffusion 3 medium, or SD3. The community has mixed feelings about it. Some folks love its text generation capabilities, while others are frustrated with the weird human bodies it creates. In This Video, You Will Learn: - The strengths and weaknesses of Stable Diffusion 3 medium in t...
ComfyUI Face Retouching Workflow Unveiled: Say Goodbye to Photoshop
มุมมอง 2.9K2 หลายเดือนก่อน
Welcome to my channel! I'm Wei, and in today's tutorial, I'll guide you through my latest workflow for AI-powered face retouching using CosXL and ComfyUI. Discover how to seamlessly add makeup, smooth skin, and enhance facial features without altering the subject's unique look. In this video, you will learn: ✨ How to download and set up the CosXL_Edit checkpoint from HuggingFace. 👁️ Step-by-ste...
AI Face Swap Battle: PuLID vs InstantID vs FaceID
มุมมอง 8K3 หลายเดือนก่อน
🚀 AI Face-Swapping Showdown: PuLID vs. InstantID vs. IP-Adapter's FaceID-V2! 🎭 Hey everyone, my name is Wei! Welcome to my channel. In this exciting tutorial, we're diving deep into a comparison of three cutting-edge AI face-swapping technologies: PuLID, InstantID, and IP-Adapter's FaceID-V2. Using a ComfyUI workflow, we'll analyze their performance and effectiveness, helping you decide which o...
Flexible Outpainting in A1111 with Dedicated Checkpoint for Inpainting
มุมมอง 7803 หลายเดือนก่อน
📌 In this video: We’re diving into a super cool technique-using Stable Diffusion for outpainting, just like Photoshop's premium feature! Photoshop’s generative fill is fantastic for seamlessly expanding photos, but it comes with a cost. What if I told you that you can achieve the same results for free? That’s right! We’ll explore how to use Stable Diffusion’s dedicated inpainting checkpoint to ...
ComfyUI Clothing Swapping: IP-Adapter V2 + FaceDetailer (DeepFashion)
มุมมอง 7K3 หลายเดือนก่อน
🌟 Welcome to an exciting tutorial where I, Wei, guide you through the revolutionary process of changing outfits on images using the latest IP-Adapter in ComfyUI. Whether you're a beginner or an advanced user, this video will equip you with the skills to seamlessly swap outfits in your images, enhancing your projects with just a few clicks. 🖹 Article Tutorial: - myaiforce.com/comfyui-ipdapter-sw...
Better Face Swap = FaceDetailer + InstantID + IP-Adapter (ComfyUI Tutorial)
มุมมอง 19K4 หลายเดือนก่อน
Discover how to use FaceDetailer, InstantID, and IP-Adapter in ComfyUI for high-quality face swaps. Achieve flawless results with our expert guide. Note: If you encounter difficulties locating the IP-Adapter Unified Loader node, please ensure that you upgrade ComfyUI to the latest version. Additionally, you should download the "IP-Adapter Plus" node available in the ComfyUI Manager, developed b...
Face Swapping in ComfyUI with LoRA (ADetailer/FaceDetailer Guide)
มุมมอง 3K4 หลายเดือนก่อน
Discover how to master face swapping in ComfyUI using LoRA. Achieve seamless, realistic results in your AI photography projects. 🖹 Article Tutorial: - myaiforce.com/face-swapping-in-comfyui-with-lora/ 🔗 Links: - Running Stable Diffusion on RunPod: runpod.io?ref=jden1933 - LoRA Training Tutorial: th-cam.com/video/sQpP8bHjHRo/w-d-xo.html - Using LoRA in ComfyUI: th-cam.com/video/WX8FIN4tz-E/w-d-x...
Test LoRAs with X/Y Plot in ComfyUI
มุมมอง 2.3K4 หลายเดือนก่อน
Learn how to efficiently test LoRA using X/Yplot in ComfyUI with our step-by-step guide. 🖹 Article Tutorial: - myaiforce.com/comfyui-lora-plot/ 🔗 Links: - Running Stable Diffusion on RunPod: runpod.io?ref=jden1933 - LoRA Training Tutorial: th-cam.com/video/sQpP8bHjHRo/w-d-xo.html - Using LoRA in ComfyUI: th-cam.com/video/WX8FIN4tz-E/w-d-xo.html
Using (multiple) LoRA in ComfyUI: A Minimalist Workflow
มุมมอง 3.5K4 หลายเดือนก่อน
Discover how to streamline your ComfyUI workflow using LoRA with our easy-to-follow guide. Boost efficiency and simplify your projects today! 🖹 Article Tutorial: - myaiforce.com/comfyui-lora/ 🔗 Links: - Running Stable Diffusion on RunPod: runpod.io?ref=jden1933 - ComfyUI LoRA examples: comfyanonymous.github.io/ComfyUI_examples/lora/ - ComfyUI manager Github page: github.com/ltdrdata/ComfyUI-Man...
How to Change Hairstyle in A1111: Two Methods Explained
มุมมอง 9894 หลายเดือนก่อน
How to Change Hairstyle in A1111: Two Methods Explained
High-Similarity Face Swapping: ControlNet IP-Adapter + Instant-ID Combo
มุมมอง 10K5 หลายเดือนก่อน
High-Similarity Face Swapping: ControlNet IP-Adapter Instant-ID Combo
Best Way to Use LoRA (LoRA + ADetailer Face Swap)
มุมมอง 2.8K5 หลายเดือนก่อน
Best Way to Use LoRA (LoRA ADetailer Face Swap)
How to Train a Highly Convincing Real-Life LoRA Model (2024 Guide)
มุมมอง 19K5 หลายเดือนก่อน
How to Train a Highly Convincing Real-Life LoRA Model (2024 Guide)
Text Inversion: The easiest way to train your face! (2024 Guide)
มุมมอง 6K6 หลายเดือนก่อน
Text Inversion: The easiest way to train your face! (2024 Guide)
IP-Adapter's New Model Surpasses Roop and Reactor: Mastering Character Consistency
มุมมอง 4.1K6 หลายเดือนก่อน
IP-Adapter's New Model Surpasses Roop and Reactor: Mastering Character Consistency
Face Swapping in A1111: Ip-Adapter Face ID Plus V2 (Better than Roop, Reactor and InstantID)
มุมมอง 18K7 หลายเดือนก่อน
Face Swapping in A1111: Ip-Adapter Face ID Plus V2 (Better than Roop, Reactor and InstantID)
Enhancing Clothing Details with DeepFashion (ADetailer) in Stable Diffusion
มุมมอง 3.8K7 หลายเดือนก่อน
Enhancing Clothing Details with DeepFashion (ADetailer) in Stable Diffusion
Mastering ADetailer in A1111(Stable Diffusion): Installation, Use and Parameter Analysis
มุมมอง 3K7 หลายเดือนก่อน
Mastering ADetailer in A1111(Stable Diffusion): Installation, Use and Parameter Analysis
Love this!!! Installed but got the following error "When loading the graph, the following node types were not found: "LayerColor: Brightness Contrast" Could you please assist? @my-ai-force. I tried downloading the raw code from Github and placed in in the custom nodes folder, tried this multiple times and still getting the error.
@my-ai-force Hi, great workflow. All working fine. But results are very bad quality, after all steps. And whatever correct image size I give, the workflow changes the image size so that my source person is badly cropped and image size and ratio are changed by your workflow. Not sure how to correct that
Amazing work, thank you for sharing it. Is there a way to use an existing image as the background instead of generating one?
How long does it take normally for me it takes with an rtx3070 and 64gb of ram more than an hour
I always got OutOfMemory even use 4090 card. All settings are same your default. When it runs to Xlabs Samplers of Generate Background, it shows out of memory. I use foto size 768 x 1536. Do you know why?
Can you show which version ComfyUI that you run this workflow pls
@@user-wi7vz2io5n Here's the link: github.com/comfyanonymous/ComfyUI/releases. I'm using 3090, and it works well.
After i updated my comfyui manager today, i can't use it, can't load the node module of Layer Style and Layercolor. I reinstall it many times. Could everyone help me? .....(Q~Q):
Have you tried to manually install these nodes without ComfyUI Manager?
@@my-ai-force Yes, i tried this way, remove the folder on the "ComfyUI\custom_nodes\ComfyUI_LayerStyle", and manually install it again, but it still can't be worked. I will try update all ComfyUI later. Thank you.
i fix it now, i update it all again, thank you
interesting workflow id like to try, thanks. altho, i cant get it running: ## Error Details - **Node Type:** KSampler - **Exception Type:** RuntimeError - **Exception Message:** mat1 and mat2 shapes cannot be multiplied (308x2048 and 768x320) any ideas? Edit: fixed that, needs another compatible checkpoint, but for some reason, the background from Relight to Repaint completly changes, and end result is just some plan colorless gray stuff
Maybe you're using the one with the gray background for repainting.
@@my-ai-force I'm using identical settings as u show 🤷
May I know which model you used in "Repaint>load ControlNet Model" ??
Is the workflow available anywhere for downloading?
I find InstantID far, very far better than the others, there is a weird thing with it: it excels to extract face features even from a "bad" picture. faceID is just good and pullID project should be closed, the most recent one yet laughably useless
great work! i ran into xlab samplers list out of index.range and couldn't figure it out. Hope someone can help
wow, thank you 🌿
You’re welcome 😊
Hi, bro! It looks like you run your Comfy as an application. When I start my Comfy on PC it runs in Browser. How can I start my Comfy also as an application?
LOL, I’m running ComfyUI in my browser too! I just went full screen to make it easier for you all to see the interface clearly.
First of all thank you very much for what you are sharing with us and teaching us without any cost. when i try to Queue Prompt i am getting an error which is below # ComfyUI Error Report ## Error Details - **Node Type:** InstantIDFaceAnalysis - **Exception Type:** AssertionError - **Exception Message:** ## Stack Trace and it appear on Node (InstantID Face Analysis).
solved.
The AI voice talks far too slow even on 1.5 speed but a really solid video, I learned a lot, always wondered how people made those comparison plots and now I know
Hello Wie, this has got to be the mother-of-all background modification workflows. Congratulations on putting this up and thank you so much. In the chapter on Background Generation using Flux - is the subject outline in the Flux image inherited from the original image or are you using text prompts to get the same outlines for the placeholder subject?
I’m glad you liked the workflow! The outline of the subject comes from the Canny edge detection applied to the original image. If you have any more questions or need further clarification, just let me know!
I did pass through the xlabs error. I am now stuck at reapaint around loading: juggernautXL_v9Rdphoto2Lightning.safetensors Need help, please. Thanks
how did you resolve it? I got the same: XlabsSampler list index out of range
You might want to download the "Juggernaut XL Lightning" checkpoint from the link provided in the video description. It’s a great resource to enhance your setup. If you need any help with the download or setup, feel free to ask!
how did you resolve the xlabs sampler error?really eager to know the solution as i have spent a whole day trying to figure it out, but no luck
I’ve been watching your TH-cam videos and using your workflows for my projects. I appreciate the value they bring. I'm seeking your help with workflows for my project using Flux-1 Dev Full Version: On my Windows 11 desktop, I'm using the Stability Matrix interface to run ComfyUI. # ComfyUI Error Report ## Error Details - **Node Type:** XlabsSampler - **Exception Type:** IndexError - **Exception Message:** list index out of range ## Stack Trace ``` Thanks! Surinder Singh
Hey I really want to try your workflow out but I am facing this error Error occurred when executing XlabsSampler: list index out of range
change image_to_image_strength to a value more than zero
Good day! When I try to start workflow I got list index out of range from xlabssampler. Did you know how to fix this issue?
Hi, it's not working for me, I'm getting an error: *Node Type:** XlabsSampler **Exception Type:** IndexError **Exception Message:** list index out of range. EDIT: The WF logic seems to be correct, it seems to be an issue with the X-Labs Sampler when it receives the Latent from the VAE Encode. It seems that it does not accept the Pixels + Vae. Replacing the controlnet model with a more stable one, like Instantx Controlnet Union or Misto Controlnet should solve the problem. Thank you very much for continuing to make WF great. !!!! Regards
Thank you again for your interest in the video and for appreciating the workflow! I’ve tested a variety of images and didn’t encounter any issues with the X-Labs Sampler. However, I did run into errors when I didn’t use “flux-dev” in the “Load Flux ControlNet” node or “flux1-dev-fp8” in the “Load Diffusion Model” node. I appreciate your suggestion to try Instantx ControlNet Union and Misto ControlNet. While I haven’t tested Misto ControlNet yet, I’ve found that Instantx ControlNet Union doesn’t perform as well as X-Labs ControlNet for my needs. If you have any more tips or questions, feel free to share!
@@my-ai-force Thank you for your great work! I've been messing around with your workflow for the past hours, it provides me with a great learning experience! While I managed to get it running with Instantx Controlnet and their nodes I keep getting this "list index out of range" with X-Labs, even when using flux-dev for the controlnet and flux1-dev-fp8 for the Diffusion Model
@@nar98 Thank you so much for catching that issue! I’ve updated the workflow to use the newly updated Xlabs Sampler, which now includes an additional “Denoising Strength” parameter. In the previous version, setting “image_to_image_strength” to 0 worked fine, but with the new Sampler, you can’t set it to 0. It’s recommended to set it to 1 instead. If you have any more questions or need further assistance, feel free to reach out!
I'd love to try out your workflow but I don't like how long it's taking to generate since I'm on 3060 12GB. How long it'staking to genzrate on wwhich GPU?
Hello. I saw some workflows on TH-cam. I downloaded them but I couldn't do them. If I showed them to you, would you prepare them for me for a fee so that I could do them?
Thank you for your interest! Right now, I'm fully focused on creating videos to provide the best content I can. While I don’t have the capacity to offer additional services at the moment, I’m glad to help with any questions or comments you have right here on the channel. Your understanding and support are much appreciated!
Well done, great job!
Thank you very much!
I’d love to be able to use your workflow but I just loaded it into my comfy and I’m missing about 40 nodes, It's very daunting to chase after each of these
I totally get it-installing these nodes can definitely be a bit of a hassle. The good news is that these nodes are quite generic and you'll likely encounter them in various workflows. Once you get the hang of how they work, you'll find that your understanding of ComfyUI will really take off. Keep at it, and you'll master it in no time!
@@my-ai-force I was able to load all the missing nodes except for two "Get_with_blank_bg" and "LayerColor : Brightness & Contrast" and idea how I can get those?
Nice! Keep em coming. Good job. 👌 Thank you
Thanks, will do!
Another great video! Thank you!
Glad you enjoyed it!
Can this all be automated and then called by an API or webhook? Thanks !
I’m afraid this technique is outside my area of expertise at the moment.
Thanks for this one. I keep getting the following error "Error occurred when executing LayerMask: PersonMaskUltra V2:" and whatever I did, did not help
Thanks for reaching out! Have you tried reloading the node or upgrading ComfyUI? Sometimes these steps can resolve the issue.
Simple and clean, Thanks
You're welcome!
thanks for this video Wei.
My pleasure!
完美😍
This workflow is really cool to play around with. Makes me want to learn more about workflows, because they seem to be really powerful. Are there any other checkpoints you recommend? or is juggernaut the best?
The Juggernaut XL Lightning version is indeed impressive in terms of speed, though the quality might not always be top-notch. Personally, I’m a fan of using Albedobase combined with a LoRA like "Midjourney Mimic". It’s worth experimenting with different setups to find what works best for your needs!
instead of generating an image is it possible to upload an image?
Absolutely, you can enhance your image using this method! First, load the image you want to improve and use the "VAE Encoder" to convert it into latent space. Then, feed it into the "Detailer" node group to refine the details. If you have any questions or need further assistance, feel free to ask!
good guide :) can you do one for hands?
You can also use Glif (cloud plateform) that allow you to generate Flux Pro image for free. No pb of realism around the skin (texture & tone), with a one line prompt and a single click. May be not reliable in the future (free Plan), but for the moment : it's simple and it's perfect (Far from Schnell).
Cant find aitana-000007.safetensors?
That’s a LoRA I trained, but you can definitely create your own as well! Check out this tutorial for a step-by-step guide on how to train your own LoRA: Watch the Tutorial: th-cam.com/video/sQpP8bHjHRo/w-d-xo.html. If you have any questions while going through it, feel free to reach out!
Awesome workflow!! Can you try adapting this workflow to perform as img2img? To produce a sort of creative upscale workflow. Would you be willing to try it?
Absolutely, you can enhance your image with this method! Start by loading your image and using the "VAE Encoder" to convert it into latent space. Then, pass it through the "Detailer" node group to refine the details. Additionally, there are upscale workflows available on OpenArt that can help you expand and customize this process further. My workflow is just a starting point, so feel free to adapt and expand it to fit your specific needs!
Great workflow!
Thanks so much for the kind words! I’m glad you found it helpful.
There must be an easier way.
Thanks ! amazingly good result but i had to use "human-parser-comfyui-node" instead of PersonMask. this one don't work for me too
dood this is shit tutorial, you forgot to feed it output pic for instantid so it know where the face should be , this is not using instantID at all if you missing the kps field
does this work for flux?
Yes, this works for Flux because the FP8 version of Flux functions similarly to other checkpoints. You can use the default ComfyUI workflow to integrate it seamlessly.
I think flux is awesome, I tried Stable diffusion on Mimicpc, and of course this product also includes popular tools for AI such as RVC, Fooocus, and others. I think it handles detail quite well too, I can't get away from detailing images in my profession and this fulfills exactly what I need for my career.
Great video but in the thumbnail it looks reversed. The before image seems to have better skin.
Oops, I missed that! Thanks so much for the kind reminder-I really appreciate it. The thumbnail’s been updated now, and I’m glad you’re keeping an eye out. Your feedback helps make this channel better!
I have an error but I don't understand what it tells me : "[Errno 13] Permission denied: 'Z:\\IA\\ComfyUI_windows_portable\\ComfyUI\\models\\mediapipe\\selfie_multiclass_256x256.tflite'" I don't understand why is it denied"?
Thanks for pointing that out! It seems like your Portable version of ComfyUI might be running into some permission issues. Could you try launching it with administrator rights? If that doesn’t do the trick, you might want to consider installing the full version of ComfyUI.
@@my-ai-force i have the Pinokio version and i have the same problem
Inside of the folder "\ComfyUI\models\mediapipe\" Make sure to have this selfie_multiclass_256x256.tflite as a file, not a folder Copy the file from inside the folder with the same name, put it elsewhere, then delete the folder with the same name and put the file there. here's the name of the file. selfie_multiclass_256x256.tflite
@@user-kf3ch7me7s did that still get an error message "incorrect path got vitmatte
@@user-kf3ch7me7s I get the same error and this is not working for me either, anyone know how to fix this?
Great stuff Wei! Very useful for me! Thank you!
Glad it was helpful!
Your video is very informative. I do have a request for the future. Try not to CONSTANTLY MOVE your screen all the time. Pick a position for what you’re talking about and let the viewer actually see. You have a habit of permanently moving the screen around, and it’s very hard to follow when the screen is never at rest.
Thank you so much for your insightful suggestions! I’m always striving to improve, and your feedback is incredibly valuable in that process. I’m excited to incorporate your ideas and make future content even better. Stay tuned!
How does your speech synthesis process look like?
Great question-thanks for bringing that up! I’ve actually switched to recording in my own voice now, so what you’re hearing is all me, no AI dubbing anymore. I hope it adds a more personal touch to the content. Thanks for your support!
hello, so what is the 2nd image for? the first one is going to match the prompt, but what does the 2nd image do again for the ipadpater?