discussion Which AI image generator do you use?

[riccs98]

I am curious which AI image generator people here use. Write which one you tried. Is it an online service or a Windows program? What do you like about it and what do you not like? Is it free or paid? What kind of images do you usually create with it? Share a short experience, and if you want, show an example too.

 

[heroahoy]

I would share but I have never done it before. I am also curious I don't know anything about it.

 

[riccs98]

No problem. I am also still learning. AI image generators are quite easy to try. Some work directly in the browser and some are Windows programs. You just write a short description and the AI creates an image. Maybe someone here can recommend a good one for beginners.

 

[Ttian]

I would share but I have never done it before. I am also curious I don't know anything about it.

Same here. Was keeping an eye in this thread to see what are some of the go tos lol

 

[riccs98]

Same here. Was keeping an eye in this thread to see what are some of the go tos lol

Same here. That is why I opened the thread. I hope people will share what they use and what works well for them. It is always easier to start when you see which tools others recommend.

 

[misterfluffums]

I feel this a good place to take a look around: AI Image Generation - Getting Started - So you wanna make some pretties?

I personally use reForge most often for local image generation. You'll need to install git to download it.

You must be registered to see links

You must be registered to see links

Re: Models, I mainly use NovaFurry, but y'know, it's for furries so I don't know how applicable it'll be for you

You must be registered to see links

For non-furries, this might be a good model for anime-esque pictures:

Can't share any examples I made, as we're outside members+ area and it's basically all NSFW XD

 

[riccs98]

I feel this a good place to take a look around: AI Image Generation - Getting Started - So you wanna make some pretties?

I personally use reForge most often for local image generation. You'll need to install git to download it.

You must be registered to see links

You must be registered to see links

Re: Models, I mainly use NovaFurry, but y'know, it's for furries so I don't know how applicable it'll be for you

You must be registered to see links

For non-furries, this might be a good model for anime-esque pictures:

Can't share any examples I made, as we're outside members+ area and it's basically all NSFW XD

Thanks for the links. I will take a look at them. I have heard about Stable Diffusion tools but I have not tried reForge yet. It looks interesting. Thanks also for the model suggestions. I am mostly interested in learning how these generators work

 

[Ttian]

Oh wonderful! My latest excursion in learning was pretty terrible. This is perfect!

 

[riccs98]

Oh wonderful! My latest excursion in learning was pretty terrible. This is perfect!

Nice. I am glad the thread helped. I am also here to learn and see what tools people use. It is interesting to see the different programs and models people recommend.

 

[Yoriko]

I use

Spoiler

You must be registered to see links

to generate images, Gemini’s Nana Banana to refine them, and I make some adjustments by hand. It’s not ideal, making something more pornographic is difficult because of Nana Banana, but it’s not impossible.

 

[Ttian]

I use

Spoiler

You must be registered to see links

to generate images, Gemini’s Nana Banana to refine them, and I make some adjustments by hand. It’s not ideal, making something more pornographic is difficult because of Nana Banana, but it’s not impossible.

Nice, another to experiment with!

 

[VSCDB]

I've tried most open source models which I was able to run. As well as multiple different of the UIs.
From the models I tried, FLUX is probably the best in general, and I usually use

You must be registered to see links

to find fine tuned models and lora's. StableDiffusion can still be pretty good tho, at least the XL variant. Have not tried SD 3/3.5 tho, 2/2.1 wasn't that good in my book. From the openly useable and home runnable models I would say FLUX takes probably the crown, you likely can't run their larger models, but even the smaller ones are quite good. I would recommend to either take the time to learn ComfyUI (it can be a bit scarry, but its been helpful to me in the long run I'd say) or go for the reforged automatics1111 UI, InvokeUI is also not too bad, but did have performance drop offs after a couple 50-100 generations.
Can't say much about the closed models.

 

[heroahoy]

You must be registered to see attachments

Here is my first ever AI generation lol

 

[Ttian]

You must be registered to see attachments

Here is my first ever AI generation lol

Looks good! Very cute!

 

[riccs98]

It turned out really good

You must be registered to see attachments

Here is my first ever AI generation lol

It turned out really good

 

[heroahoy]

It turned out really good

It turned out really good

You have inspired me to look into it lol

 

[fuzzi_weezil]

I'm just starting out and got my feet wet using Perchance. You just type what you want the image to be in the text box and select an image style and click on 'generate'. It's online and free.

You can see the stuff I've done in the public and m+ daily theme art hosted by Mime.

Here's a recent example:

You must be registered to see attachments

 

[GoonerAlien]

just selfhost your own LLM and use HuggingFace for anything you'd like.
It runs locally.

 

[rifticc]

perchance is easily accessible and pretty decent

 

[HTYYHRK]

I have Stable Diffusion installed locally, but I've never been very good at generating images with it, it's mostly for games that can take advantage of it.