Search results

To start all over is no small feat. Good for you! Glad you're still working on it, it's producing nice images!

I tried that way back a while but the faces turned into a totally different person. Glad to see the models are much better to handle that consistency now! Thanks for sharing!

Here are two workflows attached. The first is using the swap out of the WanImageToVideo node for the PainterI2V node that helps produce better movement. It also uses smaller GGUF models since I have a 3060 with 12GB VRAM. That's for generating the main video. The second workflow is for the...

I've been trying to find time to give that a go!

Did one with sound and one without, then realized if you don't want the sound you can mute it, or mux it out. Just some cute Japanese voices singing Christmas songs. Goes along with these images from the other thread...

Got some B-roll footage from the Unofficial Akiba Christmas pool party. Video link of the event at the bottom. it was wild! The occasional creepy moving object in the background, a UAP, phantom limbs underwater. :D But all in all it was a great start to the Christmas season...

I'm currently a bit fascinated with wet Christmas mature women...

Those came out nice!

ChatGPT has a nice imagination haha!

The BTS was fun! Those came out nice! I tried animating a cover a while back, an old Miki Sato Madonna cover as s test. Then I got distracted with other things and didn't go back to it. I've since done fake magazine covers that I've posted, though. Thanks for sharing!

OUTSTANDING, Zen!!!

This is my current rig for the foreseeable future. It works well for what I like doing. The quantized certainly help OOM errors or waiting a long time just to realize you produced trash :D PC: Dell XPS 8500 OS: Windows 10 Home Edition (I know...I know...) Windows 11 Home RAM: 32GB Page File...

I'm trying a different node to replace the WanImageToVideo node called PainterI2V. This one actually does produce better motion, away from the slow motion that can plague Wan 2.2 videos, especially when using the lighting 4 step loras. Of course, it could also be the source image. Video...

There can be opportunities, but eventually down the road that bubble may pop due to the exact thing we're discussing. Things will get cheaper, things will get easier, and most will start doing things locally, no need to pay for someone else to do things. Just an opinion, though, there's always...

Hey, pal, no such thing as off topic on any threads I've started! :cool: 1. From a technical perspective, is it possible to extend or modify existing movie scenes using AI? - Yes, and that seems to get better as things progress. Originally the best way to was to extract the last frame of a...

Had fun with Halloween images, now we'll skip Thanksgiving (here in the States) and head right to Christmas! Nice model to use, and it's fast. GonzaLomo XL/Flux/Pony. I used the version 4 for this (gonzalomoXLFluxPony_v40UnityXLDMD.safetensors). It's up to version 6, I'm testing with that...

Moved on to Christmas now that Halloween is over. :D Here is a video based on the images you can find in the thread below. https://mega.nz/embed/CdNQ0ITR#MmqUWNybrMvcgYiwNh1oLtoPTmThXz3_gqO65bmiPPs...

Tried this prompt with some changes because overall that's a great image it produces! Came out nice I think. Thanks for sharing! I used Forge with wildcards in the prompt, forgetting all the names I had in the name file were Japanese LOL. But, Southeast Asian came through more because of the...

Using Comfyui instead of Forge (or Automatic1111) produces different results due to the different technologies under their hoods. Another cool thing about Comfyui is that you can also use the Wan2.2 text to video model to generate images by simply generating 1 frame of video. And, it has the...

I'll see what I can do

YUP! Well, if anything I can try to make her move for you. :D

LOL OMG I just got that!

Uh oh. Where did you come across this? I dragged it to my desktop...and it is an PNG file. The format produced by AI generators. I threw it into Stable Diffusion's PNG Info tab, and it spit this out. Gonna download that model and see how I close I can get with this settings. parameters...

Here are some others I queued last night, same prompt and workflow, just fed it different images. You'll find even though they all had the same prompt, they won't all do the same thing. Probably a seed thing, I have it sent to Random after each generation, but even then based on the image...

Hey, there, sorry for the late reply, was under the weather for a bit. Good deal on trying ComfyUI, hope you're having fun with it like I am. It can seem like a lot, going strictly by the visuals of it, but once you use a workflow or two as-is getting the mentioned models in place then...

Hey, there, sorry for the late reply, was under the weather for a bit. All AI using Forge and an initial model for the text-to-image named cyberrealisticPony_v125 then resized/upscaled using a model named lucentxlPonyByKlaabu_b20 for image-to-image

I find some models create a great figures based on "simple" less descriptive prompts, while others tend to be trained on more realistic body types out there, perhaps Maybe the ideal sexy figures (to me) are not as trainable, who knows. But if I use one model that creates great bodies but not...

Wow, found one image (long gone) on Amazon Japan https://www.amazon.co.jp/-/en/Gravure-Photography-Junior-Yukari-Bikini/dp/B095P93RCG EDIT: It is from a photo book called "Topaz"? https://www.amazon.co.jp/-/en/%E3%80%8APhoto-Collection%E3%80%8BYukari-Nakai-TOPAZ-Missing/dp/B0BBHCF9YH

GREAT points!

For JAV there is interesting and exciting potential, in my opinion. Interesting in the way they are currently making JAV titles with an actress where they replace her face with a fictitious actress (I guess for those who like that) or with recognizable characters from who knows where (for those...

It's almost Halloween! Got invited to a party so I took some (not so real) photos as they were arriving but mostly heading home since I got there late. :cool:

Your other issue will be DRM. Are abke to stream it instead of download that least see it?

Are you in Japan or using a VPN as from Japan?

That is looking great!!

Brought these cuties to life using Wan 2.2. :cool: Images from this post https://www.akiba-online.com/threads/photorealistic-ai-generated-images.2123060/page-47#post-4928279 Video https://mega.nz/file/bJci2SCY#DA4s1PCWfZJW2bkH9KaF8R82cpPrxk1G9czEZFG8-1w

Videos Here: https://www.akiba-online.com/threads/ai-video-generation-general-discussion-tips-tricks-frustrations-and-showcases.2232303/page-2#post-4929004

I see your liking that outfit and model!

Is this in general or in response to a post?

I got stuck trying to make these cuties bounce around, BUT, there is more to sexy ladies than bouncing boobs, right! I should experiment with other things...but boob bouncing is nice :cool: These are the cuties from the other thread...

Did a few cuties today.

I'm still experimenting with Wan2.2, anyone else working with this or other models?

Your checkpoint looks to be coming along just fine! Great work! :D

OUTSTANDING! Thanks for sharing this! She came out beautiful!

I could NOT get a guy in a prison gray pajama outfit like I see in those opening scenes. But, the general idea was fun getting at least something almost similar... https://mega.nz/file/aNFQibxA#UCWe9IULH3gcQ5y_8zdLjey9ZB0lxPcvKoHdjOhSl8o

Very nice!!! How are handling consistent characters?

They came out pretty good! At some point I want to try for a clip that resembles what kharo88 was looking at doing. But after more experiments :cool: