[Community Challenge 31] Payback - eviltoast
Prompt

I had a fun, but difficult time making it. The image was inspired by this amazing scene in the new Fallout TV show. Getting the eyes to look over there and the finger on the trigger were the most challenging parts.

(inked original-art:1.2), (lineart:1.31), (fine-details:1.3), RAW-format, <lora:add_detail:1> <lora:realistic:.4>, <lora:3DMM_V12:0.25>, 3DMM, <lora:sharpen-soften:-0.25>, 1girl, solo, from above, long_hair, parted bangs, angry, black_hair, holding, upper_body, weapon, holding_weapon, gun, holding_gun, handgun, vaultsuit, looking at viewer, cinematic,

Negative prompt: (easynegative), (bad-hands-5), (sketch), low-res, text, watermark, (blurried-eyes), (jpeg-artifact), missing-limbs, multiple-characters, high-contrast, strong-shadows, black and white, monochrome,

Model: Arthemy Comics v5.0

This was of course followed by much upscaling and inpainting along the way.

Theme

This week, you are invited to explore the concept of “payback”. This can manifest in various forms—literal interpretations of revenge, poetic justice, or even karmic outcomes. Depict scenes that tell a story of retribution or redemption, whether in a personal, social, or abstract context.

Bonus examples:

(These are just examples of me trying to use other image generators to see if I could make what I did with SD, please do not only make images of angry women with guns! 😂)

MidJourney

Dalle

Rules:

  • Follow the community’s rules above all else
  • One comment and image per user
  • Embed image directly in the post (no external link)
  • Workflow/Prompt sharing encouraged (we’re all here for fun and learning)
  • Posts that are tied will both get the points
  • The challenge runs for 7 days from now on
  • Down votes will not be counted

Scores

At the end of the challenge each post will be scored:

Prize Points
Most upvoted +3 points
Second most upvoted +2 point
Third most upvoted +1 point
OP’s favorite +1 point
Most original +1 point
Last two entries (to compensate for less time to vote) +1 point
Prompt and workflow included +1 point

The winner gets to pick next theme! Have fun everyone!

(Secretly looking forward to seeing what Sailor Moon will get up to this week)

Previous entries

  • merde alors@sh.itjust.worksEnglish
    7·
    7 months ago

    with sd after about a hundred folds (the horrors I’ve seen). Somehow, i don’t wonder why, it was always the man that bit the “cow”. In one of the generations he even took a knife out and stabbed it 🤷

    started with a simple prompt like “a cow eating an old man” and modified it along the … diffusion.

    • theUnlikely@sopuli.xyzOPMEnglish
      1·
      7 months ago

      Total upvotes: 7

      Prize Points
      Most upvoted (tied) +3
      OP’s favorite +1
      Prompt and workflow included +0.5
      Total 4.5

      Congratulations! Your terrifying bovine has won!
      It’s your turn to think of the next challenge.

    • theUnlikely@sopuli.xyzOPMEnglish
      1·
      7 months ago

      he even took a knife out and stabbed it

      We humans aren’t going down without a fight, the bovines need to earn their revenge!

      I wanted to see what SD3 would do with that prompt…

        • theUnlikely@sopuli.xyzOPMEnglish
          1·
          7 months ago

          Yeah, but currently only via their API. The weights should be coming out sometime later. Also I’ve heard that SD3 is still undergoing training, so this current API version will probably be a bit different than the released weights.

        • theUnlikely@sopuli.xyzOPMEnglish
          1·
          7 months ago

          Yeah, I’ve seen some good generations from others, as well as some bad ones like mine here. I think it depends a lot on the prompt and I just put in “a cow eating an old man” with nothing else.

  • M0oP0o@mander.xyzMEnglish
    71·
    7 months ago

    “Zombie sailor moon reaches out of a neon swamp to swipe her debit card to buy brains from a healthy sailor moon”

    In the bingilator 16 tries.

  • ✧✨🌿Allo🌿✨✧@sh.itjust.worksEnglish
    5·
    7 months ago

    what if jesus won?

    prompt

    jesus kung fu fighting wealthy aristocrats on the temple stairs, beautiful face absolutely beautiful, action scene, jesus superpunch, slow motion, divine, masterpiece, best quality, jesus victorious, beautiful lighting, dramatic, jesus smiling, backlit, ki energy

    kung fu jesus smashin those badguys

  • Thelsim@sh.itjust.worksMEnglish
    5·
    7 months ago


    Prompt: fantasy movie still, Close-up view of a diamond on a pile of gold and a shifty thief, the thief looks greedily down at the diamond with a big smile his fingers reaching out to grab the diamond, a menacing dragon is in the background looming out of the shadows ready to eat the thief --ar 4:3 --stylize 75

    This was quite fun, having three different subjects interact with each other wasn’t easy. In most of them the dragon was either in the wrong place or merged with the thief into some kind of weird hybrid :)

    • theUnlikely@sopuli.xyzOPMEnglish
      1·
      7 months ago

      Total upvotes: 5

      Prize Points
      Second most upvoted +2
      Prompt and workflow included +1
      Total 3

      Third place and definitely a very beautiful entry!

    • theUnlikely@sopuli.xyzOPMEnglish
      1·
      7 months ago

      I love it! This brought me back to my high school history class decades ago. I can hear the teachers voice going on about the Visigoths and Ostrogoths. That was probably my favorite class. Core memory unlocked!

  • Trollivier@sh.itjust.worksEnglish
    3·
    7 months ago

    Ohhh an easy one for me! I’ve been creating a comic using the photo mode in Starfield. And I’ve complemented it using Midjourney, so I’ve got a few.

    Here’s my favorite. The prompt was : a wide close up of a young female warrior in a dark grey armor, without helmet, looking straight at us, she is visibly very angry, determined, and set for vengeance against her enemies. Behind her, we see the buildings of a futuristic cyberpunk city at night.

    That’s the moment my character realizes her best friend has been kidnapped and she suspects its because they want to get to her. And she swears to make every single kidnapper pay.

      • Trollivier@sh.itjust.worksEnglish
        2·
        7 months ago

        For this comic (it’s my only comic…), I follow a Starfield podcast that has a Discord server, and in it they organize a weekly challenge on a particular planet. I started taking screenshots every week and when I figured I had enough for a story, I created a Prologue using Midjourney.

        When I put all of it together, images, speech bubbles, I use Figma. I use ChatGPT to generate dialogues. I tell chatgpt what I want characters to say, and it suggests 5 dialogue lines every time. I pick the best one or combine different parts.

        Then export it in images and upload it on DeviantArt.

        • theUnlikely@sopuli.xyzOPMEnglish
          1·
          7 months ago

          So you upload the screenshot into MidJourney to give it a base right? Have you ever tried using img2img with Stable Diffusion?

          • Trollivier@sh.itjust.worksEnglish
            2·
            7 months ago

            I did upload one screenshot until I was happy with the rendering on the character. But now Midjourney has a way to reuse previously generated characters with the parameter cref (character reference) and cw (character weight).

            So you can just use an older character generation as a reference and tell Midjourney how much you want it to be exactly the same. If you put cw to 100 the character will have all the same clothes. If you set it to 50, it will be more creative, but it’ll be the same face, but with different details.

            I tried stable diffusion once but my computer is way too slow to generate bigger images than thumbnails. My graphic card is quite basic.

            Here are some more images I generated with the same character reference.

    • theUnlikely@sopuli.xyzOPMEnglish
      1·
      7 months ago

      Total upvotes: 4

      Prize Points
      Third most upvoted (tied) +1
      Last two submissions +1
      Total 2
    • 3volver@lemmy.worldEnglish
      1·
      7 months ago

      I’m glad I got a downvote, that’s how I know a struck a nerve. Meaningful, thank you.

      • M0oP0o@mander.xyzMEnglish
        1·
        7 months ago

        Eh we don’t count the down votes anyway. Good entry only thing wrong with your picture is the scout scope…

  • Cloudless ☼@lemmy.cafeEnglish
    3·
    7 months ago

    &lt;prompt&gt;

    classic 70s action movie poster with bold colours, a lone female character with a determined look, dusty desert town backdrop, vibrant orange sky, title ‘PAYBACK’ in bold black typography, hero holding a gun, gritty action and simmering revenge

  • Itrytoblenderrender@lemmy.worldEnglish
    31·
    7 months ago

    Sibling rivalry.

    Made with Comfyui. the Workflow Should be embedded in this picture (Catbox).

    Details

    I´ve tried to understand regional prompting with this one, but i am only a bit less confused about it now. I was able to define a workflow which gave me roughly that what i wanted to see.

    Before you adjust the masks, mute the sampler nodes. When you are satisfied with the positions of the masks, enable them again to generate a picture.

    Model:

    fenrisxl_V16fp16 (CivitAI)

    Prompt: Its complicated because of the regional prompting

    The base Prompt is:

    A boy and a girl in A beautiful childs room. The boy lays flat on the floor, the girl stands menacing over him.

    Regional Prompts:

    Full body shot of a 15 year old boy, laying flat on the floor in painful agony

    Full body shot of a 16 year old european girl, holding a pointy knife in her hand, grinning evil, threathening stance

    Full body shot of a 16 year old european girl, holding a pointy knife in her hand, grinning evil, threathening stance, red hair

    CFG: 8

    Sampler: dpmpp_3m_sde

    Scheduler: Karras

    Upscaling:

    I used a LDSR Upscaler for the final Image. Its extremly slow but seems to give the best results.

    In the Workflow is also a Face Detailer Variant. But here is the Problem that the upscaler Applies the mix of Face expression Prompts on every Face.

    Also a Iterative Upscale Variant. This one does not work at all and gives you a completly different final Picture.