Your workflow has modules that no longer work and can not be found with ComfyUI Manager. So... waste of time.
@kishirisu126828 күн бұрын
#3 image is currupted, can’t you see it? Maybe you are blind?
@manolomaruАй бұрын
😵😵😵👍
@xyzxyz324Ай бұрын
well explained! 4x upscale in my configuration in 15 min (rtx 3090 + 128 ram) --> 1792 x 960 px to (7168 x 3840 px) - 27.5 megapixels
@matthewfuller97602 күн бұрын
how much ram did you actually use/ need for that?
@user-pz2co7wg2jАй бұрын
Apisr&Supirは、Topaz Gigapixelよりも高性能ですか? Is Apisr & Supir more powerful than Topaz Gigapixel?
@RealWizardVHSАй бұрын
was the sound design inspired by Ryoji Ikeda ? sounds very similar
@prophetzarquon1922Ай бұрын
When you see this, stop driving.
@sugoidxthАй бұрын
It's a wonderful day outside, the sun is shining gleefuly, warming your skin as you wait for santa to arrive. The green autumn leaves wooshing around in the calm summer breeze, filling you with joy as you descend into madness. "Happy easter!" you say to your companion dog, it reciprocating and giving you a high-five in response.
@beaumartin7373Ай бұрын
Woag
@honkfiend7981Ай бұрын
Seriously solid, really sells the feeling of unease.
@Koz4kАй бұрын
Wow, from looking at this video I could extract a few key points: Yeah, no. What is this??? But it looks so cool.
@olejrgenbrnner4708Ай бұрын
Would be more interesting if you added a short explanation of how it was made
@mynamesgus4295Ай бұрын
super interesting
@madewhen13Ай бұрын
interesting
@JemingMyangАй бұрын
Beautiful
@sam_uel726Ай бұрын
I understand nothing. Great work!
@frankzhang7848Ай бұрын
It’s your birthday. Someone gives you a calfskin wallet.
@dangertechinc.7791Ай бұрын
You’ve got a little boy. He shows you his butterfly collection plus the killing jar.
@chaseblackstone8749Ай бұрын
0:39 id recognize red dead 2 anywhere
@Mike_AnonymousАй бұрын
That's so weird; I was only paying attention to the illustration and thought it reminded me of Emerald Station. I didn't even notice the periphery.
@yuvishira1298Ай бұрын
This Art .what was your inspiration behind it
@CamelliaFlingertАй бұрын
Nice joke, tho it's not even funny
@yuvishira1298Ай бұрын
@@CamelliaFlingert why's your ass on fire
@thomasfrade3727Ай бұрын
I didn't pay attention, and thought this was just another viral creator You can't picture my confusion when i saw that it only had 200 views Extremely underrated, amazing work
@Seven947_Ай бұрын
Thank you!
@sonnydogАй бұрын
needs more views!
@CptEmotionlessVODSАй бұрын
This is so interesting
@Seven947_Ай бұрын
Thank you!
@siddheshd9Ай бұрын
nah would rather use topaz
@TaskSwitcherifyАй бұрын
LOL - "Teeth in mouth".
@canvapikltd6305Ай бұрын
😁
@apache937Ай бұрын
did zendaya consent
@saymyname4325Ай бұрын
Does it work with sd15... I have only 6gb vram cant actually run sdxl 🥲
@anonanonymous3781Ай бұрын
You can do it even with 4 GB VRAM, however you need Tiled VAE or else you'll encounter low RAM CUDA error. Just combine tutorial or upscaler you like with it. But I see that SUPIR has "tiled_vae decoder" option, os it should work.
@Darksider-ct7quАй бұрын
Any solutions for Mac M1 pro ?
@flyingdogsoftАй бұрын
Supir is non-commercial only so what is the point of this video? research?
@apache937Ай бұрын
use it anyways no one cares
@CPDCTАй бұрын
@@apache937 lol
@101worldsАй бұрын
So perfect! Thank you
@runebinderАй бұрын
Been using this for a few days and have incorporated it into a workflow that does Txt2Img and InstantID first and it's great. Have yet to run into a VRAM issue yet, thank you :)
@matthewfuller97602 күн бұрын
what size are you upscaling to?I am guessing you have 24 gb of vram?
@runebinder2 күн бұрын
@@matthewfuller9760, I wish lol. Gott a 2080Ti with 11GB VRAM. Can reliably get around 3000 x 4000 from this, although I have dropped that down of late to 2276 x 2926 as I tend to generate a lot of portrait and found the face difficult to detail after the upscale on higher resolution. All the SUPIR is doing is a x2 resolution, you don't need 24GB for that.
@AlexanderGarzonАй бұрын
1 minute... more like 30minutes (4090 RTX, 64GRAM DDR5, AMD Ryzen 9 7900X3D and clean comfyui)
@albert93911Ай бұрын
Takes me 2 minutes flat to generate an image, run it through a few ip-adapters,a reactor node, supir to 2k and ultimate upscale to 8K. On a 3090.
@runebinderАй бұрын
I've added it to a workflow with Txt2Img, InstantID and Face Detailer and that still takes less than half an hour on my system and I've only got a 2080Ti.
@xyzxyz324Ай бұрын
sure that you are using the Lightning version of the model with required steps ?
@Lost_DawnАй бұрын
More like 3 1/2 hours for me on my POS Intel Laptop. Never buy from Walmart... And that's on Final2X since I can't Run many other image upscalers.
@trancaohuu2318Ай бұрын
I can't install Supir Traceback (most recent call last): File "E:\Data\ComfyUI-portable\ComfyUI odes.py", line 1864, in load_custom_node module_spec.loader.exec_module(module) File "<frozen importlib._bootstrap_external>", line 940, in exec_module File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed File "E:\Data\ComfyUI-portable\ComfyUI\custom_nodes\ComfyUI-SUPIR\__init__.py", line 1, in <module> from .nodes import SUPIR_Upscale File "E:\Data\ComfyUI-portable\ComfyUI\custom_nodes\ComfyUI-SUPIR odes.py", line 11, in <module> from .sgm.util import instantiate_from_config File "E:\Data\ComfyUI-portable\ComfyUI\custom_nodes\ComfyUI-SUPIR\sgm\__init__.py", line 1, in <module> from .models import AutoencodingEngine, DiffusionEngine File "E:\Data\ComfyUI-portable\ComfyUI\custom_nodes\ComfyUI-SUPIR\sgm\models\__init__.py", line 1, in <module> from .autoencoder import AutoencodingEngine File "E:\Data\ComfyUI-portable\ComfyUI\custom_nodes\ComfyUI-SUPIR\sgm\models\autoencoder.py", line 6, in <module> import pytorch_lightning as pl File "E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\pytorch_lightning\__init__.py", line 20, in <module> from pytorch_lightning import metrics # noqa: E402 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\pytorch_lightning\metrics\__init__.py", line 15, in <module> from pytorch_lightning.metrics.classification import ( # noqa: F401 File "E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\pytorch_lightning\metrics\classification\__init__.py", line 14, in <module> from pytorch_lightning.metrics.classification.accuracy import Accuracy # noqa: F401 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\pytorch_lightning\metrics\classification\accuracy.py", line 18, in <module> from pytorch_lightning.metrics.utils import deprecated_metrics, void File "E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\pytorch_lightning\metrics\utils.py", line 22, in <module> from torchmetrics.utilities.data import get_num_classes as _get_num_classes ImportError: cannot import name 'get_num_classes' from 'torchmetrics.utilities.data' (E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\torchmetrics\utilities\data.py) Cannot import E:\Data\ComfyUI-portable\ComfyUI\custom_nodes\ComfyUI-SUPIR module for custom nodes: cannot import name 'get_num_classes' from 'torchmetrics.utilities.data' (E:\Data\ComfyUI-portable\python_embeded\Lib\site-packages\torchmetrics\utilities\data.py) Can you help me ?
@genAIrationАй бұрын
Thak you!
@samsilva72092 ай бұрын
Do you know how update this workflow with ipadapter v2?
@James-kr8xmАй бұрын
have u found ways to do it yet?
@DJVARAO2 ай бұрын
It didn't work...
@doitkc2 ай бұрын
Error occurred when executing UltimateSDUpscale: mat1 and mat2 shapes cannot be multiplied (77x2048 and 768x320)
@bin3579Ай бұрын
Hello, Could you check this error? I think this error because of the version of the Controlnet
@jacobcurran75292 ай бұрын
Legend!
@ameet212 ай бұрын
You are best Thank you)
@armadillinger20822 ай бұрын
Everytime I open the comfy it comes up a error! - When loading the graph, the following node types were not found: IPAdapterApply
@autonomousreviews25212 ай бұрын
I didn't find the 'fix' section that useful, but replaced gemini with clip interrogator and find the 'upscale' section meaningful.
@justthinkaboutit79832 ай бұрын
Be aware everyone requires API key.
@grizzle20152 ай бұрын
Thank you this works extremely well. I ended up replacing gemini with WD14 Tagger and it still works really well. Tested on a lot of photos and resized images and upscaled them back up to size and this method is the best I have found for upscaling images.
@mr.entezaee2 ай бұрын
API_KEY please help me
@mr.entezaee2 ай бұрын
reason': 'API_KEY_INVALID
@mr.entezaee2 ай бұрын
\site-packages\google\ai\generativelanguage_v1beta\services\generative_service\transports est.py", line 856, in __call__ raise core_exceptions.from_http_response(response)
@realhamzabarami3 ай бұрын
u can have an even better upscale with fooocus using the variation and upscale options with nightvisionXL and epicrealism loaded as refiner at 0.4
@user-bx6kv1ik4p3 ай бұрын
works awesome... though i couldnt use gemini , had to use wd - is there a way to tweak it to upscale videos ?
@javadzohani42813 ай бұрын
This is incredible, thank you!
@juukaa6483 ай бұрын
This is the strongest Enhancer ever👍 Really great. Thx!