[ home / bans / all ] [ amv / jp / spg ] [ maho ] [ f / ec ] [ qa / b / poll ] [ tv / bann ] [ toggle-new ]

/maho/ - Magical Circuitboards

Advanced technology is indistinguishable from magic

New Reply

Options
Comment
File
Whitelist Token
Spoiler
Password
(For file deletion.)
Markup tags exist for bold, itallics, header, spoiler etc. as listed in " [options] > View Formatting "


[Return] [Bottom] [Catalog]

File:045821_IN_00001.mp4 (772.95 KB,480x480)

 No.3916

Give me a pic and I'll do an animation generation thingie with local "WAN Video". You need to include a "natural language" description of what will happen. There is an AI to autotag the general description of the static image.
For instance this was what I wrote for the OP video:
Himari BurgStrong, smooth animation. Cartoon anime animation. The girl looks around. She blinks her eyes. She lowers the blanket, revealing a hamburger. She holds the hamburger to her mouth and takes a bite. She then covers herself with the blanket and hides her face.

This was the autotag for the image:
AI TagAnime-style drawing of a cute, young girl with light pink hair and large, expressive purple eyes. She is wearing a white hooded cloak with a hood, and is sitting on a red couch. The background is a simple, dark brown gradient. The girl's expression is neutral, and she is looking directly at the viewer. The image has a soft, pastel color palette. The style is clean and detailed, with a focus on the character's delicate features and soft shading.

I can do NSFW too since it's a local model, but that should be on the appropriate board. *cough*
I'm trying to figure out the painful installation of this 'sage attention' thing that is supposed to half generation time, but until then I'm going to limit the size and duration of things. It took me 3 minutes to generate this, which is definitely not right. Not sure how I was able to do 50 second generations a couple days ago...

 No.3917

File:__hatsune_miku_and_roon_vo….jpg (454.89 KB,1000x1000)

Having this Roon offer you a slice of cake

 No.3918

Is this the current standard for local video generation, or is there anything somewhat close to this recent "Veo 3" thingy or what it was called? I heard about that one just a day ago and it looks very impressive, but seems to be gated by G**gle.

 No.3919

File:062340_OG_00001.mp4 (532.91 KB,480x480)

>>3917
That's not really describing anything. She's already offering a cake.

>>3918
I'm not exactly an expert at it since I just now got hardware able to do it. You can get it to like 12 seconds or something, but the processing is exponential the longer you go. The online models are certainly far better.
The upside is that you could do porn with it without working at google or otherwise having a privileged position. Presumably a higher level of control, but this ComfyUI program is god awful and I hate looking at it. I don't think I'll be able to tolerate this video stuff for very long due to how horrendous the UI experience is.
It seems like unfortunately the real life stuff is far better, so good news for people that want to do deepfakes or cause strife in the real world.

 No.3920

>>3916
This burger just bit this shab.

 No.3921

File:skibidi skibidi skibidi sk….png (427.73 KB,496x684)

Make a 2D anime girl stick her head out of the toilet and morph into this 3D woman end result

 No.3922

>>3921
I don't think that's possible. Well, it's certainly not with my knowledge at least. For best results I need to start with an image with most of the detail already there and then this AI video can move it around in vaguely understandable ways.
There's a text-to-video option, but I haven't tried it yet and there's no way it will compare to actual 2D models for static images.

 No.3923

>>3919
What hardware are you using in particular, if I may ask?

 No.3924

File:explorer_bLvq7dy0jF.png (8.08 KB,449x287)

>>3923
You can ask! I did some major upgrades this year due to the economic chaos caused by retards making bad decisions.
The 5090 that I got just last weekend is doing the bulk of the work, but some of it is being offloaded to DD5 memory. I'm trying to get this thing called "sage attention" to work, but it's been very difficult due to software upgrading at different times and I quite seem to get everything synced up correctly.
"SCRIPT FAILED! You're using Version 1.294.12941 of Script Thing. You need 1.294.12939!"
WARNING! Script Thing 1.294.12939 is incompatible with Decompiler Thing 2.9291B!"
It's really a marvel at any of this AI stuff works at all due to all the dependencies and separate scripts and everything. This pic is from cleaning up a few installations when troubleshooting.

 No.3936

>>3922
>I don't think that's possible. Well, it's certainly not with my knowledge at least.
Ok, then something simpler with that pic please.
When you're generating videos, is the input pic necessarily the first frame of the video? I recall the Sora demos of multiple videos that held the final frame constant, so different sequences of events would play out and converge to the same final scene in a way that felt very uncanny due to how improbable such a thing would be. Can you do something like that for the skibidi toilet girl?

 No.3942

File:172119_IN_00001.mp4 (2.16 MB,600x720)

Consider this.

 No.3943

File:204248_IN_00001.mp4 (1.01 MB,600x720)

>>3936
I'm really new to this. All I know how to do is take an image and animate it... somewhat. You're asking me to do the things that billion-dollar data centers are doing and I'm not sure that I can. Local models have some pretty heavy limitations even if there's some freedom involved with the lack of censorship.
Well, here's a vid. I just said "head bopping up and down with extremely long neck" and as I type this it's generating and I'm not sure if it will work.

In the future I don't want to do real life images like this, but you can see that it's pretty impressive technologically. But isn't as fun or cute as 2D stuff.

 No.3944

>>3943
also this model is supposed to be focused on more fantasy/2D stuff. I didn't download the real life model that would probably be better at real life images.

 No.3945

>>3943
omg I really like that result, thank you

 No.3946

File:86361288_p0.jpg (1.4 MB,2067x1447)

can you make her pat her belly with パチパチ sound effects and close her eyes and burp

 No.3947

File:__roon_and_leipzig_azur_la….jpg (456.75 KB,1512x1080)

I am requesting that this Roon is patting her belly with a content sigh as Leipzig watches on.

 No.3948

File:212818_IN_00001.mp4 (2.09 MB,720x480)

>>3946
No idea how I'd generate sound lines so I didn't bother. This is very uncanny. Definitely not the Koruri I know and love. Still, pretty impressive. I need to try again.

 No.3949

>>3948
she looks like she is aggressively masturbating....

 No.3950

File:213436_IN_00001.mp4 (3.41 MB,720x480)

KORURI NO WTF. AI sure is weird...

 No.3951

how strange

 No.3952

File:214104_IN_00001.mp4 (3.12 MB,720x480)

I guess the first one was closest. This might be a prompt thing, although it's also early-ish tech and with static images people could generate dozens in the time it takes to make one of these so it's easier to get a good one.
Sorry, Koruri, your cuteness just can't be captured by AI.

 No.3953

>>3950
KORURI WATCH FOR THE ASTRAL DEMONS WHEN PROJECTING OR THEY'LL CATCH YOU

 No.3954

File:214808_IN_00001.mp4 (1.86 MB,720x480)

Okay I think I'm done trying with Koruri. Something about the prompt or her position is just freaking it out. It didn't even animate the first few seconds here.

 No.3955

File:215713_IN_00001.mp4 (1.14 MB,720x480)

>>3947
This stuff really is unpredictable. This looks really dumb, but then there will be a good one appear out of nowhere. I'll try again...

 No.3956

It keeps trying to smoothly interpolate and fade stuff in and out. Maybe it says it's a video model intended for 2D animation but I don't buy it, I reckon even video models finetuned for 2D will still do 3D better.

 No.3957

File:220340_IN_00001.mp4 (1.28 MB,720x480)

heh this is kind of funny

 No.3958

File:164255_IN_00001.mp4 (3.01 MB,600x720)

The weird thing is it animated the AI Kuons from SD quite well. Maybe it has difficulty on human stuff for some inexplicable reason.

 No.3959

File:tech_support.jpg (327.51 KB,900x1000)

What about these lolis running and bouncing around the desk?

 No.3960

>>3943
Wtf I love skibidi toilet now

 No.3961

>>3959
this guy draws really cute lolis

 No.3962

File:010904_IN_00001.mp4 (4.17 MB,600x720)

>>3959
hehe I'll have to make a few of these. Very coherent and steady/

 No.3963

File:011707_IN_00001.mp4 (2.84 MB,600x720)

Hmmmm.... still not very great. I wonder if there's a trick to writing the intended movement.

 No.3964

File:012458_IN_00001.mp4 (2.47 MB,600x720)

For this generation I reduced the "Shift", although I don't know what that means. I would take a guess that maybe it means how dramatic it is in changing the scene? ALso increased CFG which generally means it follows the prompt more at the cost of less "freedom". Hmm this might be a good idea.
This is it for the lolis... at least for now. I'd like to come back once I know what I'm doing.
I really don't know why the results are so bad...

 No.3965

File:1488839270115.jpg (172.05 KB,851x774)

thanks for your efforts thus far

animated version of this tehepero pls




[Return] [Top] [Catalog] [Post a Reply]
Delete Post [ ]

[ home / bans / all ] [ amv / jp / spg ] [ maho ] [ f / ec ] [ qa / b / poll ] [ tv / bann ] [ toggle-new ]