Even_Adder

joined 1 year ago
sorted by: new top controversial old
1
Mug’s Plea (image.civitai.com)
 

(AIMon86) (2024)

Image description: A white mug with a sad face design on its surface, placed on a wooden table. The mug is illuminated by warm sunlight coming from the window behind it. A speech bubble above the mug contains the text “Feed me,”.

Full Generation Parameters:

Beautiful award-winning photo. POV looking inside a sad and empty coffee cup. Gorgeous early morning light. Kitchen table. Beautiful lighting. Shallow depth of field, volumetric lighting, film grain, cinematic. A text bubble next to the coffee cup reads, “Feed me.”

Steps: 25, CFG scale: 3.5, Sampler: Undefined, Seed: 791129173, Size: 832x1216, Created Date: 2024-09-13T1226:06.5333070Z, Clip skip: 2

12
Solitude Woods (image.civitai.com)
 

(OdiousStooge) (2024)

Image description: A cloaked figure seated by the edge of a tranquil body of water, within an autumnal forest setting. The trees are dense and display vibrant shades of orange and red. An ethereal glow emanates from behind the trees, casting a warm golden glow over the scene, which contrasts with the cool blue tones of twilight that permeate through the forest canopy and reflect off the water’s surface.

Full Generation Parameters:

A wide-angle shot of a winding river cutting through a dense autumn forest, the water glowing with an eerie, pale blue light as ancient magic flows through it. On the riverbank, a lone human shaman in a fur-lined cloak kneels, casting stones into the water, watching as the ripples form strange symbols. Behind him, tall trees with crimson leaves stand like sentinels, their branches whispering in the wind. The sky above is darkening, the last light of dusk fading into a deep purple. The vibe is mystical and foreboding, with nature and magic in perfect harmony. , Vibrant, grotesque, and surreal with bold contrasts, heavy black outlines, and a blend of dreamlike autumnal hues; a mix of neon, retro, and pagan elements, inspired by Sean Aaberg’s punk-infused, chaotic energy and dreamcore's eerie, nostalgic undertones , the scene is captured in dimly lit dark fantasy but vibrant colors, with bold ink lines defining form against the watercolor wash of the aged paper

Negative prompt: BadDream, worst quality, low quality, normal quality, monochrome, grayscale, text, signature, watermark

Steps: 37, CFG scale: 3.5, Sampler: DPM++ 2M Karras, Seed: 2465658560, Size: 832x1216, Created Date: 2024-09-16T1130:46.7125312Z, Clip skip: 2

10
Hashy Comfort (image.civitai.com)
 

(wonderfulbody) (2024)

Image description: A single-seater sofa made of shredded hash browns with a textured yellow surface. The sofa is on a wooden floor in a room lit by natural sunlight coming through a window, casting shadows on the wall and floor. A round wall clock hangs above the sofa, a green plant on the left, and there’s an indistinct, framed artwork on the wall to the right.

Full Generation Parameters:

cinematic shot of a sofa made of shredded hash browns in a modern room, the sofa cushions are made of hash brown patties <lora:Hash_Brown_Flux:1>

Steps: 20, CFG scale: 1, Sampler: Euler, Seed: 966125460, Size: 896x1152, Model: flux1-dev-bnb-nf4-v2, Version: f2.0.1v1.10.1-previous-527-g720b80da, Module 1: ae, Module 2: t5xxl_fp16, Module 3: clip_l, Model hash: bea01d51bd, Schedule type: Simple, Distilled CFG Scale: 3.5

4
Python Sundae (image.civitai.com)
 

(AnimePorn) (2024)

Image description: A snake wrapped around a classic ice cream sundae glass topped with sprinkles, whipped cream, and a cherry. The background is a gradient of purple to a rainbow hued surface beneath the sundae glass.

Full Generation Parameters:

Steps: 25, CFG scale: 3.5, Sampler: Euler, Seed: 0, Size: 1025x1025, Model: , Version: ComfyUI, Model hash:

GenAI Slop in c/[email protected]
[–] [email protected] 0 points 1 day ago* (last edited 1 day ago)

I wanna believe you, but the JPEG artifacts on an image that small make it extremely difficult to even notice the distortions you're referring to, especially at a glance. You've made it obvious you're replying in bad faith, so I'm gonna leave it here. Have a good one.

GenAI Slop in c/[email protected]
[–] [email protected] 0 points 1 day ago (2 children)

That's a lot of things to infer off of just scrolling past a 512×768 JPEG. If the image was in another context and the text had been different, no one would have batted an eye.

GenAI Slop in c/[email protected]
[–] [email protected] 0 points 1 day ago (4 children)

That isn't extremely obvious though, especially with the JPEG compression. If you didn't know to look, you wouldn't have noticed it. No one scrutinizes Jeopardy text.

GenAI Slop in c/[email protected]
[–] [email protected] 0 points 1 day ago* (last edited 1 day ago) (6 children)

Yeah, but the point isn't to look like a legit Jeopardy clue, it just has to not look generated. You can respect the height limit if you want, or break it.

Your reply also wasn't in the form of a question. No points.

7
Flight of the Boar (image.civitai.com)
 

(Raylom) (2024)

Image description: A winged boar in mid-flight against a backdrop of towering mountains and a blue sky. The boar has large, feathered wings spread wide, and its fur is gray in color.

Full Generation Parameters:

A realistic shaggy boar flies in the sky. It has large gray shaggy wings the same color as its skin. Mountain far away. 8k, hyperrealism, detailed.

Steps: 20, CFG scale: 1, Sampler: Euler, Seed: 3576085929, Size: 896x1152, Model: flux1-dev-bnb-nf4-v2, Version: f2.0.1v1.10.1-previous-501-g668e87f9, Model hash: fef37763b8, Schedule type: Simple, Distilled CFG Scale: 3.5, Diffusion in Low Bits: Automatic (fp16 LoRA)

22
Lost Among Twisted Trees (image.civitai.com)
 

(novuschroma) (2024)

Image description: A stylized Viking figure, standing in the center of a forest setting with an overcast sky. The figure is adorned with a horned helmet, has an orange beard, and wears a purple cloak over purple armor. In the figure’s right hand is a large axe. Surrounding the figure are twisted, bare trees and scattered rocks on the ground; along with some yellow flowers.

Full Generation Parameters:

novuschroma51 style viking claymation <lora:novuschroma51 style_claymation:1>

Steps: 30, CFG scale: 7, Sampler: DPM++ 2M, Seed: 481036390, Size: 896x1152, Model: Faetastic_v24, Version: v1.10.0, Model hash: 07b985d12f, Schedule type: Karras

GenAI Slop in c/[email protected]
[–] [email protected] -2 points 1 day ago

I think something innocuous or inoffensive enough to most people qualify as "good looking". I mean, that's how marketing works.

20
Menacing Moon (image.civitai.com)
 

(oddKoodoo) (2024)

Image description: A large, elongated monolithic stone hovering above a desert landscape under a red sky with an oversized sun. In the distance, there is a small figure next to a vehicle observing the phenomenon.

Full Generation Parameters:

professional photo of a landscape, scenery from another world, red planet, endless red desert, huge orange sun, black oval elongated stone monolith hovering in air, several small dark figures standing underneath levitating monolith, BREAK, BEST QUALITY, MASTERPIECE, HIGHLY-DETAILED, HIGH-RES, 4K, 8K, RAW, SHARP FOCUS, INTRICATE DETAILS,

Negative prompt: WORST QUALITY, LOW QUALITY, LOW-RES, JPEG-ARTIFACTS, WATERMARK, (woman, bush, tree, grass, mountain, cliff,:1.2)

Steps: 15, CFG scale: 5.5, Sampler: DPM++ 2M, Seed: 41412668, Size: 960x1280, Model: XL omniGen v1, Version: v1.7.0-1224-g82a973c0, Model hash: 79559d6cf7, Schedule type: Karras, Denoising strength: 0.8, Downcast alphas_cumprod: True, Clip skip: 2

GenAI Slop in c/[email protected]
[–] [email protected] -2 points 2 days ago (8 children)

A generated image could be so good you'd never be able to tell. Like this one:

[Steve Mould] This new type of illusion is really hard to make in c/[email protected]
[–] [email protected] 7 points 2 days ago (1 children)

That was really cool.

GenAI Slop in c/[email protected]
[–] [email protected] 1 points 2 days ago (12 children)

I think the real complaint here is about bad looking art. Not a lot of people have an eye for picking out good-looking images. Or this person is just a huge snob.

Curling Porter in c/[email protected]
[–] [email protected] 1 points 2 days ago (1 children)

That's low right? I just thought the slogan was funny.

Stable Diffusion 3 Medium Fine-tuning Tutorial — Stability AI in c/[email protected]
[–] [email protected] 0 points 2 days ago

Those might just be LoRA merged models, not full fine-tuning. From what I heard, fine-tuning doesn't work because the models are distilled. You'd have to find a way to undistill them to train them.

Stable Diffusion 3 Medium Fine-tuning Tutorial — Stability AI in c/[email protected]
[–] [email protected] 0 points 2 days ago (2 children)

Last I heard, LoRAs cause catastrophic forgetting in the model, and full fine-tuning doesn't really work.

4
Curling Porter (image.civitai.com)
 

(Reyn__) (2024)

Image description: A single aluminum can of beer placed on an icy surface. The can is labeled ‘CURLING PORTER’ in large, bold letters at the top. Below the title, there’s an illustration of a curling stone with the phrase “slides down your throat” is printed above in smaller font, playfully alluding to both the smoothness of the drink and the action of curling stones sliding across ice. At the bottom of the label, there’s additional text including what appears to be alcohol content listed as “2.9%,”.

Full Generation Parameters:

The image is a photograph of a can of Curling Beer. The main text "CURLING PORTER" is written in bold, blue letters with a white underline and a black outline. Below the main text, it reads "Slides down your throat" in smaller letters. The small text at the bottom of the can says: "2.9%". The can features a detailed, vibrant illustration of a curling puck. The can is sitting on ice in an ice sports arena.

Steps: 24, CFG scale: 3.5, Sampler: Undefined, Seed: 4174156182, Size: 832x1216, extra: [object Object], Created Date: 2024-09-15T1008:09.1843054Z, Clip skip: 2

This self-taught Japanese composer is behind some of the most beloved video game music in c/[email protected]
[–] [email protected] 8 points 2 days ago

You can never learn anything with these clickbait headlines.

9
In-Depth Guide for Training Logos With FLUX DEV (www.finetuners.ai)
8
Wire Deer (image.civitai.com)
 

(ThruAIEyes) (2024)

Image description: A wireframe deer in a forest setting. The deer is intricately designed, with numerous intersecting lines that form the shape of the deer. The sun is shining brightly through the trees directly behind the deer, creating a radiant backlight effect and casting elongated shadows on the forest floor.

Full Generation Parameters:

Wireframe model of a deer standing in a forest clearing with sunlight breaking through the trees

Steps: 8, Sampler: euler, Seed: 120749442030657, Size: 832x1216, Model: flux1-schnell, Version: ComfyUI, CFG Scale: 1.0, Model hash: 9403429E00

11
Stable Diffusion 3 Medium Fine-tuning Tutorial — Stability AI (stability.ai)
24
Silent Season (image.civitai.com)
 

(VolatileSupernova) (2024)

Image description: An elderly man with a long, flowing white beard and hair, wearing a red robe adorned with blue, green, and yellow floral patterns. His expression is contemplative, with a meditative look on his face. The man is positioned slightly to the right, with his head tilted slightly upward, gazing into the distance. In the background, a large, tree with a thick trunk and branches stands prominently to the left. The tree's branches are filled with vibrant orange leaves. The sky is blue, with a few scattered clouds, and the ground below is covered in dry, golden grass.

Full Generation Parameters:

Anime Style, in a surreal and dreamlike scene, the iconic artist Katsushika Rogers stands tall with her long beard glinting in the sunlight. Her signature blue eyes are closed as she gazes out at the stunning backdrop of a Baobab tree, soft focus, Visual novel, Depth of field 100mm

Steps: 25, Sampler: Euler, Seed: 637041270817705, VAE: FluxVae.safetensors, Lora_0 Model hash: eb95ac4c95, Lora_0 Model name: Anime style.safetensors, Lora_0 Strength clip: 1, Lora_0 Strength model: 1

view more: next ›