The Ultimate Superheroines Forum

How it was done...

• Create an original static picture in DALL-E3 using a text prompt (see below.)
• Take the image into hailuoai.video to animate it.
• Create some dialogue using voice changer in 11Labs.
• Use Vozo to get the lips in the video to sync with the new voice audio.
• Glue it all together with your favourite video editor, and maybe add some background sound effects.

... and voila!

R5

<div style="position:relative; width:100%; height:0px; padding-bottom:100.000%"><iframe allow="fullscreen" allowfullscreen height="100%" src="" width="100%" style="border:none; width:100%; height:100%; position:absolute; left:0px; top:0px; overflow:hidden;"></iframe></div>
Go to sleep Batgirl!!! Just Relax into it!!!! I've got big plans with you! HHHHMMMMWWWWAAAAA!!!!!!!!!!!!!

R5

This should be fun to play around with...

BlackOut wrote: ↑

1 year ago

This should be fun to play around with...

That is more than just walking with a head shake and a smile.

This is great, will have to try it. Have you tried ImageFX? I find it much better than Dalle3.

https://ibb.co/album/J5PycX

More examples. It takes some finessing with the prompts but I'm happy with the results.

Been working on this today - started it off with a text to video prompt and have been taking the end frames from each clip to continue the animation further - voices added in via Eleven Labs - touch up editing done in Clipchamp.

BlackOut wrote: ↑

1 year ago

Been working on this today - started it off with a text to video prompt and have been taking the end frames from each clip to continue the animation further - voices added in via Eleven Labs - touch up editing done in Clipchamp.

Did you use the voice changer in 11Labs, or the text-to-speech? Generally speaking if you choose one of the pro quality voices that have been highly trained (there are quite a few available to free accounts) you'll get much more interesting results with voice changer. With t2s you're relying on the algorithm to guess the cadence from the text, but with voice changer you can record yourself saying the dialogue exactly how you'd like the AI voice to say it. The pro voices will even do giggles, laughs, grunts, gasps, exclamations, sarcasm, whispers, etc. -- which the t2s absolutely cannot do!

There's a handful of useful pro voices that I've found, available to free accounts. For example, "Jessica Anne Bogart" has a slightly husky American female accent; "Brittney - Young, Peppy" has a youthful American female accent, light but not too girly; "Donny" is a male super deep movie trailer voice; etc... There's just far too many to list.

EDIT: Some further notes... The first video I posted uses Jessica Anne Bogart, which is an American voice but I recorded the audio with a posh British accent as an experiment (to try to match the Victorian setting.) What came out is a kind of hybrid trans-Atlantic voice, which sounds quite nice. But I've noted, while experimenting, that it helps if you can mimic the speech patterns of the AI voice accent you're using. For example, if you speak English but choose a Chinese voice you get something that sounds really rather racist. Although the accent is authentically Chinese, the cadence of the voice and the way certain sounds are pronounced (or mispronounced) is inauthentic. So it doesn't sound like a native Chinese speaker struggling to get their tongue around English pronunciations, rather it sounds like Benny Hill doing a 'comedy Chinaman' skit. (Out of curiosity I watched some YouTube videos by a Hollywood voice coach, and he explained the secret to an authentic Asian-speaking-English voice is how double consonants at the ends of words, and repeating consonants between words, are vocalised. And also the voice timbre. There's more to it than mispronouncing your R's like Benny Hill. )


R5

Blackout
five_red
thegreengiant - well done!

This popped up on my feed yesterday:



It's a basic YouTube video on the cars that appeared in the show, and the footage is all straight from the show.

Where the AI comes in is that they've done a simulated Lynda Carter voice for the narration.

BlackOut wrote: ↑

1 year ago

This should be fun to play around with...

What program did you use to get the voice? The vid? It's incredible


Or is the Vid and Voice all in one?

infogeek247 wrote: ↑

1 year ago

BlackOut wrote: ↑

1 year ago

This should be fun to play around with...

What program did you use to get the voice? The vid? It's incredible


Or is the Vid and Voice all in one?

Ideogram for the image, hailou for the animation, 11labs for the voice, and Vozo for the lip sync.

Thank you.
There are so many, what would you suggest for text to image? SFW and NSFW?

Next comes 8 minutes mini stories!

I was initially one of those who were very sceptical of AI when it first began but now I see it just the way hand drawn artists probably viewed Poser and DAZ back in the day. It wont replace older methods completely but it will definitely have its place.
The sudden jump in AI animations is what stuns me intensely. We are on the cusp of seeing so many peoples fantasies come to life in realistic or cartoon ways. For instance, its incredible to see things like wonderwoman struggling against realistic octopuses in her tight hotpants.
I only hope i live long enough to see full length AI superheroine peril movies. Like most things, it will be the imagination that makes it hot, not the technology.
I raise my hat to all of you who are making these very hot AI superheroine scenes!

Ok... so I went and gave it the "ol college try...

If someone knows how to extrapolate the video and post it as an image like the examples above, then by all means please do so (I'm computer literate, but not that tech savvy with embedding).

jca5646 wrote: ↑

1 year ago

If someone knows how to extrapolate the video and post it as an image like the examples above, then by all means please do so (I'm computer literate, but not that tech savvy with embedding).

Go to streamable.com and upload your video. Get the embed web link (that's the URL of the video, not the HTML code) and post it into the full editor on this site (not the quick reply box) and if you ask for a preview you should find the editor has recognised the site and automatically turned it into an embedded video.

R5

.

Ok, round two (hopefully successful in posting preview)

<iframe allow="fullscreen" allowfullscreen height="720" src="" width="720" style="border:none;"></iframe>

https://www.deviantart.com/taurus2861/a ... 1105414536

If you wanted to put like a "CNN" banner or something on your vis, how would that be done?