• We are currently rolling out incremental alterations to the forum. Don't freak! You aren't going crazy.

Chat AI Creations and Vs Debates

Cryso Agori

V.I.P. Member

Lmao, so batman apparently already had a way to stop the missile but decided to wait till he's like almost dead.
 

Limu&Doug

Acclaimed
V.I.P. Member


Pack it up boys
 

Cryso Agori

V.I.P. Member
 

Cryso Agori

V.I.P. Member

another draw.
 

Cryso Agori

V.I.P. Member

bruh, lmao

AI shutara is haxed gaddamn.
 

Masterblack06

Man of Atom
Moderator
@Solar Sailor the ai has given its opinion on your thread
 

Masterblack06

Man of Atom
Moderator
@Top59 @Xhominid The Apex

 

Cryso Agori

V.I.P. Member
On the general topic of AI, did not know DALL-E could do shit like this, but imagine making DALL-E 3 turn versus prompts into actual comic strips used for depiction instead of a wall of text?


@Thegoldenboy2188 get on dat ASAP
I will when I get home, thanks for showing this too me

Off but also on-topic I've been wondering if it's possible to make a similar multi-modal image gen with SD.

Stable Diffusion while can generate images as good if not better than Dalle-3 especially with XL, requires a ton of add-ons to do so, mainly because SD is built to generate images first, understand text second, which means that it can't understand prompts or sentences as well as Bing Image Creator, which uses ChatGPT as its prompt understander meaning that it understands text way better.

I was wondering if its possible to use a Llama freeware, and train it on English and understanding prompts, so that it can understand sentences and as such multiple subjects way better. Then connect it to SD.

Problem is how to translate the info from the llama to SD without losing any information (thus losing multi-modality). I ain't a coder (yet) so I have no clue how it could be done but as far as I'm aware the idea is sound.

Infact fooocus is basically a weaker version of this.
 
Reactions: Ral

Atem

King of Games
V.I.P. Member
Arlan Vorlesh versus Yhwach.


The Knight Commander be like: "You're going to jail, bitch."

 

Cryso Agori

V.I.P. Member
Thinking on this more, said llama freeware would probably also need to be able to understand images too.

GPT-4 can actually understand and caption images pretty accurately, which is probably why Dalle-3 can generate well. So it would need to have image recognition capabilities to, it would also allow higher img2img capabilities.

Extending this, if this second "Prompt AI" can understand both text and images, to be able to caption it too. You can probably use it to train itself too. Similar to CLIP or BLIP.

Another thing is perhaps adding a GAN to it. For example, Style-GAN-Human based off the research is way better at creating humans than diffusion models.


Mainly hands look like hands, unlike Diffusion models.

So I'm wondering if you can connect it together in a pipeline like Prompter AI(understands prompt)->Diffusion(generates broad conceptual image based on prompt)->GAN(draws over with precision based on prompt and SD image)

This way if you want a realistic human, it can do it with good hands.

However problem is that GAN's unlike diffusion models are very specific, Diffusion models can take a concept and apply it to a lot of things (like john wick is a cartoon style). While GAN's can only generate a specific thing, a GAN trained on realistic faces can't make a cartoon face.

So maybe a pipeline where we switch GAN and Diffusion would work.

Prompter AI(understands prompt)->GAN(draws precise image based on prompt)->Diffusion(draws over precise image with stylized art based off prompt and GAN image)

However there are base GAN's capable of generating different concepts. So perhaps its possible to use StyleGAN3 maybe that can work together with the Diffusion model.

only problem is hardware space, and how much ram it would take to run what's basically 3 dnn's at the same time lol.
 

Atem

King of Games
V.I.P. Member
The Hero of Kvatch versus The Batman Who Larps.

 
Yuri defeating Yhwach. Seraphic Radiance is overkill.
 

Atem

King of Games
V.I.P. Member
ChatGPT doesn't know that countenance means physical appearance. I tried fair skin, and it didn't work "because that would be offensive." I exchanged it for countenance instead, and it works. It gets pass the censors.

Soma Cruz enters Netflix Castlevania.