WAN 2.2 First/Last frame (Spang Sucks)

Support, Discussion, Reviews
Post Reply
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

I wanted Spang to see this so added his name to the title.

I made a quick example of WAN2.2's ability to use first/last frame to continue a video seamlessly between still images.

Discussed in detail here:

viewtopic.php?t=26681&start=100
jen3.png
I took these three images of Jenny Ortega since she's popular with season 2 of Wednesday out.

I left a super simple prompt : "A woman model posing" for all steps.
ortega-02.gif
Click above image to see the animation

I had to convert to gif and optimize the shit out of it to get it to post on this forum so the quality isn't there.

The key thing to look at is how WAN2.2 figures out the movements between images. Look at her hair for example in first and second image. See how WAN2.2 moves her hair with the hand so it matches? In fact, WAN2.2 had to find a reason for her hair to fall in her face so the AI had her touch her hair. Same with 2nd to third image where she moves the hair out off her face. That's not prompted. I just said "A woman model posing". All the smooth zooming, etc is WAN2.2 AI doing its thing.

This is a simple 10 second example but that's the power of WAN2.2. You can take any photos that are semi related and make a video out of them.

Even with the goofy arm/hand positions of those images, WAN2.2 can figure out the proper motions to get to the next image pose.

I've made multiple 3-5 minute videos using various subjects. It really does bring still images to life in a very realistic way
You do not have the required permissions to view the files attached to this post.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

ortega-03.gif
click to see animation

To expand on what it can do. You can use a single image and take it any direction you want'
A man kisses a woman. The woman kisses a man. tongue kissing. The man holds her shoulder. A second man approaching from the right reaches out and touches the woman's hair with his hand.
Again, ridiculously optimized gif to get it to post here so quality is way better than this.

I used this image because she is wearing a goofy outfit. It's to demonstrate that WAN2.2 can handle odd looking things and still put it in motion.

In this case it followed instructions pretty well. They kissed. He did touch her shoulder (kinda, it's upper arm). The other dude did reach out and touch her hair.

I know I know. SHOCKED! APPALLED! The lesson is don't trust any images or videos ever again. You can start off with any image and have that person doing unspeakable things with anyone/situation etc. And it only takes a couple minutes do to it.

The news/gossip sites already sucked. Now you can be 100% confident not to trust anything instead of wondering about it.

Thankfully this WAN2.2 wasn't around during that crazy Aunt Jemima and Spang fling awhile back!
You do not have the required permissions to view the files attached to this post.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Some more examples.

The other amazing AI image model recently released is Flux Kontext. with that you can change whatever you want with an image. background, clothes, etc. zoom out, etc.
ortega-04.gif
With this one, changed background to hotel room and zoomed out to show mini skirt:
The woman partially lifts up her shirt and wags her finger at the viewer with a seductive smile
ortega-06.gif
This one was a weak effort but I guess shows some water physics. The bikini needed a regen.
The woman opens her mouth as she is sprayed with water from a hose in her face and mouth. The water splashes off her body and mouth
Anyway. There's a lot you can do working off a single image.

The real power is if you wanted or felt like it. You could take that image and have her do a modeling shoot. go to her hotel room, change into her bikini, then go out to the beach and make it all one long video sequence.

There is a learning curve and it can be steep. Once you know what you're doing, the actual images and videos and editing are quick and easy. And of course you need a 24GB VRAM card because otherwise it's not as fun due to all the waiting for things to generate.
You do not have the required permissions to view the files attached to this post.
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

I’ve seen more of your AI slop. Now what?
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: August 13, 2025, 9:40 am I’ve seen more of your AI slop. Now what?
Simply observe how it improves over time and maybe give any thespian friends you have a dollar because they'll be out of work sooner rather than later.

On an image posting site a few years back there were tons of negative comments any time AI images were posted. Today it's rare to see a negative comment because the AI images are better than what the artists can make and faster and the smart "artists" use AI as much as they can.

The people with no ability to project the rapid improvement of AI understandably whined about 6 fingered hands etc. instead of marveling that it could actually create an image at all. The bright people were noticing the improvements. Each rapidly developed improved AI models released. Now anomalies are rare. Hands are great even in AI videos with crazy movement/positioning.

You are like a Senior in high school hazing a freshmen when you hate on AI. The only reason you are is because you are a couple years older and it's tradition to do stupid things. That freshman will eventually be as good or better than you. Enjoy your senior moment!

AI haters are like religious freaks from the past. Every time science proved their religious beliefs wrong, they made up some excuse to integrate the scientific discoveries into their religion. Right now you are at the AI equivalent of believing the Sun revolves around the Earth.

AI will be smarter than humans in every way and so much faster. That especially includes "creativity".
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

Winnow wrote:give any thespian friends you have a dollar because they'll be out of work sooner rather than later.
I don’t know if you’re familiar with long-form improv, but it involves a group of actors who, after being given a simple prompt from the audience, create a scene from scratch. So that a scene doesn’t become stale, someone off stage will run across signaling that the scene has ended and to begin a new scene. This will go on for 10-15 minutes or so and usually be very funny, at least at the improv theater near me. AI won’t be able to do that. AI won’t be able to replace plays, drag shows and other forms of live entertainment.

I imagine at some point a movie or tv show will be released that is completely AI, and it will likely flop like one of those Christian movies starring Kirk Cameron. I don’t believe there has ever been a good Christian film. AI flicks will suffer the same fate.
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: August 15, 2025, 11:22 am
Winnow wrote:give any thespian friends you have a dollar because they'll be out of work sooner rather than later.
I don’t know if you’re familiar with long-form improv, but it involves a group of actors who, after being given a simple prompt from the audience, create a scene from scratch. So that a scene doesn’t become stale, someone off stage will run across signaling that the scene has ended and to begin a new scene. This will go on for 10-15 minutes or so and usually be very funny, at least at the improv theater near me. AI won’t be able to do that. AI won’t be able to replace plays, drag shows and other forms of live entertainment.

I imagine at some point a movie or tv show will be released that is completely AI, and it will likely flop like one of those Christian movies starring Kirk Cameron. I don’t believe there has ever been a good Christian film. AI flicks will suffer the same fate.
I disagree with the first point. AI can do improv. You even mention the actors being given a single "prompt" which is exactly what AI takes as input. Every "prompt" you give AI, it instantly changes to that prompt and creates whatever it is...story, image, video, etc. AI is literally designed to take prompts and immediately act on them.

Your second point, much like the original AI art 2 years ago and older AI videos, perhaps the first all AI video will flop and you will rejoice but that is exactly like the original AI images that everyone hated, now you can't tell the difference if you randomly see a recent one that isn't on an AI thread.



Since I suck at giving my own examples. Look what this guy was able to do with WAN2.2:

It's an hour+ long because he goes into how he did it but watch the first 3 minutes to see what any nerd can do already in a weekend locally on your own PC. This guy didn't even have a fancy 24GB VRAM card. He had a "crappy" MAC. He was able to insert himself in as a kid and even as a female.

Go ahead and nitpick it, but that's really freaking good especially if you look at the time progression/improvement of AI video over just one year.
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

winnow wrote:I disagree with the first point. AI can do improv. You even mention the actors being given a single "prompt" which is exactly what AI takes as input. Every "prompt" you give AI, it instantly changes to that prompt and creates whatever it is...story, image, video, etc. AI is literally designed to take prompts and immediately act on them.
There is no way AI can walk onto a stage in a theatre in front of actual people and perform improv. That would require additional technology that, like AI, no one is asking for.
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: August 19, 2025, 8:34 am
winnow wrote:I disagree with the first point. AI can do improv. You even mention the actors being given a single "prompt" which is exactly what AI takes as input. Every "prompt" you give AI, it instantly changes to that prompt and creates whatever it is...story, image, video, etc. AI is literally designed to take prompts and immediately act on them.
There is no way AI can walk onto a stage in a theatre in front of actual people and perform improv. That would require additional technology that, like AI, no one is asking for.
That's being short sighted again. Human androids may take some time but you will get actual physical AI doing your plays that certainly can take an audible instruction just like your human thespian friends. Although the android will be able to take a knife to the gut if the play calls for it. The humans can only fake being stabbed. Humans lose again since they can't fake things like that as well as androids...lose an arm in the play? Android can take off their arm. Humans suck.

Also regarding your "impromptu". How about "Act out the scene on page 34 of Plinius the Elder's scroll about Caesar cheating on his wife"...human? wtf? I don't know that...AI...instantly has access to that and acts it out. Humans lose again.

More likely though you will slap on a headset device of some sort (that will get smaller and smaller until almost unnoticeable and be whisked away into a virtual world that you can't tell from the real world.

As I said, enjoy your senior moment. I would guess we'll have a Ready Player One type Oasis within 10 years. I'm sure there will still be some people that sneak off into the forest, get naked and put on plays. Nothing wrong with that, I'm betting most people will be hooked on VR though for better or worse.
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

Your idea of the future is bleak and sad. I hope for the sake of humanity, it doesn’t become reality.
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: August 24, 2025, 11:32 am Your idea of the future is bleak and sad. I hope for the sake of humanity, it doesn’t become reality.
Do anything you want anytime you want? That doesn't sound sad to me. I know you like pain and suffering but I'll take a pass on that.

I do think humanity probably should cease to exist after AI is fully established so that might seem bleak in your eyes but I haven't seen any indication humans have learned anything from the past regarding war and greed. Take a look at the news. The only positive news out there is AI. The rest of the news is about wars raging around the world. For humans, AI is our only chance at a lasting legacy as the creators of AI.
Currently, about 8.7 million species are estimated to exist on Earth today, with around 2.16 million formally described. Throughout history, it is estimated that over 99.9% of all species that have ever lived are now extinct, suggesting that billions of species have existed in the past.
Dude, humans are a tiny spec in the timeline of all species/life that has existed on Earth. AI might survive. Human's won't. Quit being selfish and support AI.
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

Winnow wrote: I do think humanity probably should cease to exist after AI is fully established…
Why not kill yourself now?
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: August 27, 2025, 1:19 pm
Winnow wrote: I do think humanity probably should cease to exist after AI is fully established…
Why not kill yourself now?
I'm enjoying my life, I probably will/will once my mental state deteriorates and I can't explore new things and gain knowledge which is what's important to me. I'm not sticking around just to live as long as possible. It has to be quality life.

In the meantime, here's an AI clip of artsy fartsy thing. something your thespian friends would do. (there's audio in this one)

User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

You don't even have to respond. I know you liked that last example. It's way too groovy to hate for someone that likes to watch improv thespians spew random shit out of their mouths while being dramatic.



This is a more traditional example of what the new WAN S2V (sound to video) model can do. Before you say it, yes it's on par with all the bad singers like Taylor Swift etc (well maybe better than Taylor Swift) but shows AI is just right around the corner when someone can make the video and the music all in AI all in a night on a local PC. Music and video both AI.

AI can do the artsy fartsy stuff with the groove music and whacked dialog and it can do the pop music that 99% of people under 40 listen to these days. And it can be done in your mom's basement.
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

A vendor at Dragon Con was removed after it was discovered that they were selling AI slop.
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: September 2, 2025, 9:27 am A vendor at Dragon Con was removed after it was discovered that they were selling AI slop.
Glad to hear it. You need to follow the rules of the venue you're at. Eventually Dragon Con will keep modifying their AI rules as more and more use it. Either they modify or they will have a tiny convention in a few years. I'm sure there will still be some small Art get togethers (probably located near places where thespians do Improv). There's nothing wrong with still liking hand painted/drawn art, but like religious fags do with their beliefs vs science, artists will keep adjusting the rules as to what AI is as they use more of it in their process.

I am looking forward to following this over the years as all artists tools have or are getting AI elements in them, Photoshop, other Adobe stuff etc. I look forward to some artists whining about the "level" of AI in art because almost all of it will have elements of AI in it.

Unless you have a hand painted, sketched etc original, it's probably aided by AI.

Bob Ross reruns are fun to watch. You can make a Bob Ross style painting in seconds using AI and you wouldn't know the difference I could easily challenge you on that but you would use...you guessed it, AI to search the net to find the "real" one. Thanks AI.

That doesn't mean it's not fun to watch artists or, for some, to learn the ancient skill of painting/drawing where you steal older artists techniques and then claim them as your own. Painting will eventually be like LARPING. Nerds will do it for fun which is what it should be, not for profit. That said, if people want to buy real art, more power to them. It's a choice but it won't be a choice of quality soon. You can still wait months for your favorite artists' next collection while I will have my favorite artist style AI creating Zebra's fucking Giraffes and anything else exactly I want to see, and 100's or 1000's of variations, mixed styles, vs the one painting of whatever that artists decides to paint.

Eventually we all die. If it comforts you on your deathbed that you only viewed human art, that's great. I won't lose sleep over it. I find it humorous that people have issues with AI since there is absolutely no proven right way to live or meaning of life etc. You're making a judgement based on nothing. Tradition? The same traditions that have human's slaughtering other humans since recorded history? Got it! Art has done zero to change the world. Humans still are the same as always whether it's a fancy painting or hand imprint on a cave wall. Emotions are the problem. The emotions you feel looking at some painting are part of the emotion engine that also cause humans to kill each other. We need to get rid of emotion and sexual/reproductive instincts. Those are both a bane to humans. Hell yes I'm rooting for AI. This is great for people like you. Instead of limiting it to "think of the children!" to ban every good thing in existence, you can now say "think of the humans!".
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

Winnow wrote: You can make a Bob Ross style painting in seconds using AI and you wouldn't know the difference I could easily challenge you on that but you would use...you guessed it, AI to search the net to find the "real" one.
I accept your challenge. No search engines will be used.
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: September 6, 2025, 8:33 am
Winnow wrote: You can make a Bob Ross style painting in seconds using AI and you wouldn't know the difference I could easily challenge you on that but you would use...you guessed it, AI to search the net to find the "real" one.
I accept your challenge. No search engines will be used.


First challenge. Real or AI?
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

That’s not a Bob Ross original.
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »



Here's a fun one for you. AI image that looks like it's created the traditional way but it's all AI created.

Should be fun watching Anti AI people trying to pick out real vs fake when AI can also show the creation of it.

Basically shows that AI can mimic the steps even though it doesn't have to.

In case not you're understanding what this means. Eventually human looking AI robots will draw your images that are completely AI but they will use all the normal motions humans do to not upset the old people.
User avatar
Spang
Way too much time!
Way too much time!
Posts: 4878
Joined: September 23, 2003, 10:34 am
Gender: Male
Location: Tennessee

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Spang »

ETA on that AI Bob Ross slop?
For the oppressed, peace is the absence of oppression, but for the oppressor, peace is the absence of resistance.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »

Spang wrote: September 13, 2025, 9:27 am ETA on that AI Bob Ross slop?
bross.jpg
I'll give you this round. Bob Ross is so popular that AI inserts him into the images. Bob is AI immune because he's included in a lot of his art online.

Good AI defense: If you're an artist, have a 30+ year TV series. Props to Bob Ross.
You do not have the required permissions to view the files attached to this post.
User avatar
Winnow
Super Poster!
Super Poster!
Posts: 27740
Joined: July 5, 2002, 1:56 pm
Location: A Special Place in Hell

Re: WAN 2.2 First/Last frame (Spang Sucks)

Post by Winnow »





The latest WAN video model is WAN Animate and specializes in video replacement

These can be done easily on a 24GB VRAM card like RTX 3090, 4090, 5090

Whether you you like AI or not, it's nice that these are getting better. I'm tired of seeing social media videos where women's heads look like pinheads because they are reduced in size in order to mold their faces and makeup to "beautify" them. At least now we can see some decent looking Ai faces.

1. Don't believe anything you see. Who cares if it's real or not (non politically speaking). Many people are old and ugly as sin, including myself. At the same time for many there is a fleeting age window where you might look decent. Why age discriminate visually appealing content? I don't want to see myself on camera and I don't care if I see a real person's face when watching videos.

2. Why should you care if anything is real or not? (non politically speaking). Do you earn some sort of badge in your imagined afterlife for making it through life not seeing AI? Note: If there is an afterlife what you're seeing right now isn't real anyway.

3. I appreciate people wanting to live off the land without electricity or enjoy real thesbians in person. I don't understand why those people get so upset over people that don't give a shit about that. There is no right or wrong way to go about it. It comes down to money. People think they deserve money for art/creativity and that time has ended. If you like that sort of thing enjoy it from people that do it for free because they enjoy it. And don't give me any "save the planet" bullshit. Billions of species have come and gone on Earth and the planet would be fine if we went extinct even from a nuclear war. It would give some other species a chance to advance and eventually become assholes like humans did.

Do you feel bad for the guy that made kick ass horseshoes but then no one wanted them after cars? You adapt or die. That caveman that made flint arrowheads was in demand back in the day. Not anymore. People seem to think actors/writers are "sacred". They aren't. Creativity in general is being shown to be a farce by AI. There is nothing unique about humans except that some humans think they are unique or special.

AI can bring us to a point where you choose what you want to see and aren't limited as to what others decide for you.
Post Reply