Video

great, now I only need the vram

👍👍

share the workflow?

czcams.com/users/shortsKig_xfUt77U

I believe this model is specifically for anime. Any other style of animation comes out wonky.

You say 26gb of ram needed, but could one skimp by on a lowly 2900XTX? with 24GB?

Me with my 4060 8gb ram thinking I got this: Sees: the comments: Well then let me delete the github repository

I’m mad it’s not good enough.

I want to know how to install it. difficult difficult

This is all free on Kali Linux

Sora already disrupted this just as AI LLMs have disrupted OBM

Is it a tutorial for "how to create a new folder"? man, are you serious??

what if i tried the color mode on my 4080? more importantly how do you do it??

For anyone getting a syntax error after the last step he forgot to put an = after auth in the last step

I installed it localy on Windows using my 4070Ti, and waited 10-15 minutes to generate a video, but nothing happened. Can you make a specific tutorial for Windows users?

Awesome! 🎉

How can i use the color feature or sketch guidance

Thanks for sharing! Bummer about the VRAM requirements, yikes.

That result looked kinda bad ngl man Oo

What about a Mac Book Pro M1 Max 64gbs?

Dang, so even my 4090 can't handle this huh. Here's hoping the 5090 has 32GBs of Vram.

👍👍

Aaaand another channel calling this a 2 Minutes Tuesday. Because the CZcams Gods know that if you want to succeed on the platform, you need to have Peter McKinnon's style topped with MrBeast's font. 😆

I'm having trouble with the <install -r requirements.txt> command, tried joining the discord but it seems the invite link has expired. I'm on Linux and haven't had this happen with any other dependencies I have installed

There are even more dystopian ramifications to cloud computing vs. edge computing. Not only is your data vulnerable to exposure, theft, and corruption from a single source provider when using 'The Cloud 😶‍🌫😇👹', in the long run it also sets up those providers as the gatekeepers of information. They, and they alone, will decide who gets access to what censored information and services. Once they control the information, they can also completely control the total social narrative and discussion. Information is power, and there are those in the world ruthless enough that they will stop at nothing to accumulate more, or even more preferably ALL. "We are the priests of the Temples of Syrinx Our great computers fill our hallowed halls We are the priests of the Temples of Syrinx All the gifts of life are held within these walls" Rush - 2112 The whole '2112' story arc itself feels eerily prophetic given our current trajectory. 🖖👺👍

Thank you for making the video! very clear and understandable. Looking forward to part 2!!!

dude you're god!!! thank you so much! instant sub!!

This is great thanks!

thank you for this, i think you're the only one on here who did an indepth comfy tutorial for ays. It made me realize i absolutely do not need it in my workflow looool. The difference is not that huge compared to what they showcased in their paper.

This doesn't work I keep on getting the message No module named "insightface"

thanks

Error occurred when executing IPAdapterTiled: insightface model is required for FaceID models followed every step including the requirements.txt

Feel like you should have done some masking on the ipadapters especially the dress one instead of trying to work around it picking up the woman

What all of these workflows, including this one, have in common is that they are totally irrelevant (as of now) for e-commerce because of these "minor details" that AI always gets wrong. How would this be interesting for e-commerce if AI does not depict the garment correctly?

workflow plz.. sir :)

Cool! Thanks so much.

Thank you, I've been looking for an alternative to the Lightning Loras without sacrificing negative prompt, this fits the bill.

Exactly what I was looking for. Thank you!

Where exactly is the workflow on your website?

SO far SO GREAT!! More detail in faces. Render SPEED x3. Played very nicely indeed with IPAdapters and controlnet workflow. Lora not used as not needed. Nice one!!

I still can't get over how terrible eyes look in SDXL.

so la la

via Pi The best use of AYS with Cascade "When working with Stable Diffusion Cascade and ComfyUI on an Nvidia GPU, a recommended workflow would involve setting up the Ays (asymmetric step) node to double the number of steps you'd typically use for img2img generation. Then, split the sigmas at the halfway point using the SplitSigmas node, and feed only the second half to the k-sampler. Here's a brief summary of the workflow steps: 1. Set the Ays node steps to double the usual amount (e.g., 20 steps instead of 10). 2. Use a SplitSigmas node to divide the Ays output at the halfway point (e.g., at step 10 for 20 steps). 3. Connect the second half of the SplitSigmas output to the k-sampler input. This workflow takes advantage of the capabilities of Nvidia GPUs and optimizes the use of Stable Diffusion Cascade within ComfyUI. Keep in mind that some adjustments might be needed depending on your specific hardware configuration and desired results."

via Pi "After a thorough search, I can confirm that Stable Diffusion Cascade does indeed use the DPM++ sampler, along with other samplers like DDIM, Euler, Heun, and LMS. DPM++ is considered a high-quality sampler that produces detailed images, although it can be slower than some other options. It's part of the family of DPM solvers designed specifically for diffusion models, and it's known for its accuracy and image quality. So, to answer your question, yes, Stable Diffusion Cascade does use the DPM++ sampler!"

you are amazing but : You are presenting a podcast on a video that contains an image that does not move

The workflow link provided doesn't work.

How to stop server?

I'm sorry, but your video is kind of strange, it feels like there's a filter applied that blurs the image and makes your eyes hurt. If possible, don't use it again.

I will stick with Turbo and Lightning models for now.