59
Forefathers one and all, bear witness! (lemmy.world)
submitted 7 months ago by myfaceistupid@lemmy.world to c/imageai@sh.itjust.works
11 comments fedilink hide all child comments

Elden ring inspired. Kinda hard to get bing image creator to create a dragon-hand. Probably doable with Stablediffusion and some inpainting.

top 11 comments
sorted by: hot top controversial new old
[-] toothpaste_sandwich@feddit.nl 8 points 7 months ago

Wow... Very impressive though. Real big comic book vibe.

[-] Dindonmasker@sh.itjust.works 6 points 7 months ago

The one time we want more arms then needed they aren't there...

[-] Leg@lemmy.world 5 points 7 months ago

That letter H goes so hard.

[-] LazaroFilm@lemmy.world 5 points 7 months ago

What was the prompt? Love the comic book style.

[-] myfaceistupid@lemmy.world 4 points 7 months ago

Prompt for the main image is:

gritty graphic novel art, a warrior holding up his hand which has turned into the head of a fire breathing dragon and shouting "forefathers one and all, bear witness!" speech bubble

[-] LazaroFilm@lemmy.world 3 points 7 months ago

Sweet! I tried and modified your prompt to try to remove the hand and was able to get a decent result. i got this.

The prompt was:

gritty graphic novel art, a warrior holding up his the stomp of his cut off hand upon which has been attached the head of a fire breathing dragon and shouting "forefathers one and all, bear witness!" speech bubble. make sure no hand is holding the dragon’s head.

[-] sirico@feddit.uk 3 points 7 months ago

Surtr!

[-] merde@sh.itjust.works 3 points 7 months ago* (last edited 7 months ago)

i still can't control text in generations. It seems to be easier on Bing? How do you prompt for text on stableDiffusion?

[-] myfaceistupid@lemmy.world 5 points 7 months ago* (last edited 7 months ago)

Text is a lot easier on bing/dalle 3, for stable diffusion, its better to just do it manually, or use controlnet. There are loras like this one though: https://civitai.com/models/176555/harrlogos-xl-finally-custom-text-generation-in-sd

But its mostly for logos, and still takes a bit of prompting to get it to write what you want.

[-] Danquebec@sh.itjust.works 2 points 7 months ago

I'm subscribed to both metal and imageai. I had to check where this was coming from.

[-] Mrkawfee@lemmy.world 2 points 7 months ago

This is great.

this post was submitted on 12 Apr 2024
59 points (100.0% liked)

AI Generated Images

7166 readers
155 users here now

Community for AI image generation. Any models are allowed. Creativity is valuable! It is recommended to post the model used for reference, but not a rule.

No explicit violence, gore, or nudity.

This is not a NSFW community although exceptions are sometimes made. Any NSFW posts must be marked as NSFW and may be removed at any moderator's discretion. Any suggestive imagery may be removed at any time.

Refer to https://lemmynsfw.com/ for any NSFW imagery.

No misconduct: Harassment, Abuse or assault, Bullying, Illegal activity, Discrimination, Racism, Trolling, Bigotry.

AI Generated Videos are allowed under the same rules. Photosensitivity warning required for any flashing videos.

To embed images type:

“![](put image url in here)”

Follow all sh.itjust.works rules.

Community Challenge Past Entries

Related communities:

founded 1 year ago
MODERATORS
god@sh.itjust.works
noodle@sh.itjust.works
TendieMaster69@midwest.social
theUnlikely@sopuli.xyz
thelsim@sh.itjust.works
M0oP0o@mander.xyz
Deceptichum@quokk.au