Відео

i made a custom gpt for gpt4 that converts prompts/sentences to wd 1.4 tag prompts. it's called '(BooruKai_Prompter: 1.4)' "### Example Prompt Conversion: - **Original Sentence**: "A sci-fi cyberpunk heroine in an industrial area, wielding futuristic weapons." - **Token-Sparse Prompt**: "1girl, cyberpunk, weapon, industrial_area, futuristic, short_hair, blue_eyes, armor, neon, machinery""

the music is amazing, is it AI made too?

Pretty cool idea. Looking forward to it. And AutoStudio you talked about, do similar image generation. But yours are build on workflow and run all of this. What backend SQL and code you will be use for the next update?

it can be integrated like LBX Studio, but for better AI Video Model, not SVD. 🤭

For Freebies : www.patreon.com/posts/stable-diffusion-107319629 Goodies For Patreon Supporters: www.patreon.com/posts/create-story-llm-107317948 If you need to setup Local Ollama to host your local LLM with ComfyUI. Here's previous tutorials : 1 - ua-cam.com/video/EQZWyn9eCFE/v-deo.html 2 - ua-cam.com/video/yR2Y9G71w6E/v-deo.html

Hey can you prompt the Florence2 model on what parts of an image you want to describe? Example Describe the background only or Describe the person in detail only! or are there better vision models for this?

That's nice. But I don't know how to feel about that. It's funny and disturbing at the same time. I mean, theses are not real people, one day they might have some kind of chatgpt-like actors that will have "Lora-models" attached to them ... and will "live" inside the machine to provide their movie. Honestly disturbing future of AI on the mankind.

I'd love to have lightweight workflows to try theses out

ViewDiff: 3D-Consistent Image Generation lukashoel.github.io/ViewDiff/ MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model myniuuu.github.io/MOFA_Video/ github.com/MyNiuuu/MOFA-Video huggingface.co/MyNiuuu/MOFA-Video-Hybrid AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation howe183.github.io/AutoStudio.io/ github.com/donahowe/AutoStudio

WOnder when we can get access to these models?

Cool... now I wonder about VRAM requirements for these tasks... any info on that?

Please provide links

Looks like Auto Studio can work with AI video generator. Create storytelling images then Img2Vid. Using Luma AI, Gen 3, Kling or maybe Sora later.

Mofa video , will they do in ComfyUi node?

How to use inpainting and change something from the excisting picture?

wow amazing and How did you get consistent characters

Pretty good! Only a few morphs for long video

круто и просто..

very nice !

👍

So from best to worst: 1) Open AI Sora 2) Kling AI 3) Luma Labs 4) Runway Gen 2 (this one very far) . Runway Gen 3 I do not know how to qualify it.

Would love to be able to play with this, but alsa it seems not for us peasants 😭 I like the level of consistency in each scene, unlike luma which to often mutilates faces if they move even a fraction, but they did add start and stop frames which is something I guess.

Global warming is so bad those friends are melting and shifting like ice-cream

@benji - another great video. If you can nail the expressions and blinking, that would be amazing!

Wonderful thank you. No one else on UA-cam is covering this

it killed my comfyui, i wont start anymore. i only tried the first node with the manager. RIP.

The app is in English for me, how do I get Chinese?

using spacepxl node, i am getting strange polygons for all images i try to run region to segmentation on. The captioning is working correct. any ideas?

i tried fastblend on Automatic1111 is very very slow, i tried to increase the batch but take all my 24gb vram and 96gb of ram, what parameters are better for a video in 1920*1080?

Can 8gb vram handle this😅

2 hours and smooth video node has not moved an inch, with vid 2 vid , 60 frames cap , lcm cp and lora, tried again and again

stupidity ai LOL... ROFL...

Can I do this in a RTX 3060 gpu

Fantastic work, like always

I get error at realistic line art for some reason? Do you know how to resolve this? Thanks

It works on stableswarm ui

Hey man any tutorial / workflow on your video 2 video method? Thanks in advance: )

I watched the video and tried to follow along. I saw this error message on the video combine node side. Error occurred when executing VHS_VideoCombine: Cannot handle this data type: (1, 1, 512, 3), |u1 The only thing I changed the settings to is The SD1.5 version checkpoint I have and This is about the size of a sample video. The rest of the settings were the same, but an error occurred.

will get blurry result if the stylize image pattern (edges, contrast) is different from the original image due to the blending algorithm; Need extra steps to deblur

does Google Colab approve usage of stable diffusion notes?

GTX 1650 super work ?😢😢

There are other nodes, I don't remember the name now, but what do you say detect me such a thing, and it generates the automatic mask, (but not square) but with its real contour,

thanks! where was the comfyui node/workflow?

Cool stuff. Would have been good for dance videos but sadly will get a copyright strike on UA-cam.

This is wonderful. I assume this is not SXDL ready yet, right?

This is fun , 1 code can do anime video. I will try it.