FLUX with FACE ENHANCER 🔥 - Using ComfyUI locally (With Low VRAM and LORA Support)
ฝัง
- เผยแพร่เมื่อ 12 ก.ย. 2024
- Yo, I am back with one of my fav workflows of all time. you must have noticed that when you create an image in flux with either full body or where the face is smaller, the details get messed up. Now you can upscale the whole image but what fi you already like the image and just wanted to have the face a bit better ? I have a workflow to enhance the face AUTOMATICALLY and it even supports LORA.
IMPORTANT ⚠️
I have used a LORA of Sydney Sweeny just to show the workflow capability to use LORA in face, and I tried to create LORA of my face but couldn't create it well and the results were not good so had to use one from CIVIT AI. NEVER USE SOMEONE ELSE'S LORA / FACE EVEN IF YOU FIND ABUNDANCE ON CIVIT AI OR OTHER WEBSITES, NEVER EVEN FOR ANY PERSONAL USE !
Links 🔗
Workflow - app.box.com/s/...
Unet Model (Main FLUX)- huggingface.co...
t5-v1_1-xxl-encoder GGUF- huggingface.co...
VAE- huggingface.co... (just ae.safetensors file)
Clip_L - huggingface.co...
ComfyUI- github.com/com...
Music track: Latency by Chill Pulse
Source: freetouse.com/...
Free Music No Copyright (Safe)
If you are looking for face enhancer, flux face enhancer, comfy ui face enhancer, comfyui face detailer, florence 2, SAM2, ideogram 2.0, Flux AI, realistic AI images, AI image generation, flux realism, AI art tutorial, segmind models, realistic AI art, Flux AI tutorial, AI image creation, advanced AI imaging, Flux realism LoRA, flux ai image generator, free ai image generator, midjourney alternative, Flux ai free, flux ai realistic guide, best ai tools, flux.1, flux ai images, custom flux, custom flux.1, flux.1 lora, lora flux, lora flux.1, easy guide to ai image, ai image gen, midjourney consistent character v6, stable diffusion, gen 3 video, ai news, open ai, flux 1, AI imaging techniques, realistic AI generation, Flux AI workflow, AI art creation, image synthesis, AI-powered creativity, photorealistic AI, Flux AI tips and tricks, AI art tools comparison, next-gen AI imaging, Flux AI for beginners, advanced AI art techniques, AI image enhancement, Flux AI vs other generators, AI art community, cutting-edge AI technology, AI image customization, Flux AI best practices, AI art inspiration, future of AI imaging then you will love this video.
This channel is underrated, I hope you get the thousands of subscribers you deserve soon.
Very good workflow. It worked from the start. Good job, and thank you!
Brilliant workflow, just tried it and it works great. Thanks for sharing and providing a video that explains things.
other guides used FLUX with SDXL or SD 1.5 for face detailing, but this guide uses FLUX face detailing with LLM. I tried it out and it's great-no loss in detail at all! Thx!
Perfect addition to your upscaler, nice work. Your segmentation can be simpler by using layermask tho.
great video, thank you for sharing !
Very nice work however I'm on an M1 MacBook Pro and cannot get past the Sam2Segmentation node in the Face Enhancer section of the workflow... Getting a 'RuntimeError: Input type (c10::Half) and bias type (float) should be the same' error......
Any ideas from anyone here on how to fix it , if it's indeed possible ??
Device is set to MPS instead of Cuda.
how I can get the same execution time on every node?
Hello
Do you know why your Loara was bad ? Actually I have very good result with only 12 images. I tried other with 60 of images just for test.
So does the original image you started with have to be a Flux generated image ?? If it can be a just a photo then can we use a this worlflow for doing a high res face swap with a LoRA generated face ??
Yes technically you can, but you will have to finetune the parameters. Most times there's some texture / lighting difference which will although work but make it feel like somethings off
Really keen to know what you think on my questions ? Can we swap a high res face on a photo from a fine tuned Flux LoRA of another person ?? You mentioned you wanted to use your own LoRA generated face but did not due to poor quality
Thank you for the video. Where did you find the loras for the detailer?
CivitAI, you can find all the loras there 💯
@@xclbrxtra Thank you but I can't find them 🥲🥲😔😔
I didn't understand how only the face on the photo uploaded improve and which nodes need to be disabled?
Enable the image 2 image and reduce steps, and keep face switch on
@@xclbrxtra In which node (give me the node name in workflow) i need reduce steps? do you mean "face switch on"
enable Enable Face Enhancer in Fast Groups Muter (rgthree) node? or something else specify the specific nodes of the name where I need to perform the actions. I enable in Fast Groups Muter (rgthree) node image 2 image and upload photo, but it still generates a new photo without processing the face on the uploaded photo.
Milion tutorials how to use FLUX it in Comfy UI and very few how to set everything to work in normal UI for ordinary people and none how to use Controlnet or IP Adapters without Comfy UI involved.
Controlnet and Ipadapters are not that good in flux till now, they don't give SDXL level results. Apart from that if you install ComfyUI, I already have provided workflows so you just need to input prompts that's it. I just explain the logic so if someone wants to tweak something,they can. You can just drag my workflow and it's ready to use.
if i want to put a celebrity's face on a marble stone statue, would this workflow get me there? if not, can you recommend one?
Technically it should, if you use some lora trained on statues and another lora of the celebrity. Recently the IPAdapter for flux also released but it doesn't work that well for now, maybe in future they update it.
Can we use face enhancer for video?
does it work with only 32GB ram?
It will work with 16 gb ram too if you have a decent graphic card
As soon as ANYone enters the visual nightmare of comfy UI BYE BYE!!
bot
Git gud.