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.
Last I heard, LoRAs cause catastrophic forgetting in the model, and full fine-tuning doesn't really work.
(lambda_san) (2024)
Image description: A young woman with teal eyes and long, pastel pink hair cascading down her back. She has a cheerful, open-mouthed smile. She is wearing a medieval-style outfit with a blue tabard over a beige, puffed-sleeve blouse and a blue skirt. The blouse has a high collar with a gold trim. She also wears a gold necklace with a large, ornate pendant. Her outfit is complemented by a brown leather belt and thigh-high white stockings. She is seated on a stone ledge, her hands resting on her lap. The background features an outdoor scene including tall trees and a flowing waterfall in the distance. The sky is bright blue with white clouds, and the ground is covered in various shades of green grass and flowers.
Full Generation Parameters:
rurubell (megami paradise), long hair, pink hair, blue eyes, jewelry, bracelet, necklace, short sleeves, pendant, blue skirt, zettai ryouiki, white thighhighs, brown footwear, boots, 1990s (style), retro artstyle, <lora:rurubell (megami paradise)_pony_v1:1> sitting, dynamic pose , open mouth, blush,light smile looking at viewer,(cowboy shot:1.3), outdoors,, masterpiece, best quality, score_9, score_8_up, score_7_up, best quapoty, highres, absurdres, source_anime, zPDXL2, 1girl, Negative prompt: score_6_up, score_5_up, score_4_up,,score_3, score_2, score_1, source_pony, worst quality, low quality, lowres, artist_name, text, missing fingers, extra digit, fewer digits, jpeg artifacts, signature, watermark, username, blurry, censored, bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, hyperrealistic, ,mosaic censoring, negativeXL_D,zPDXL2-neg,unaestheticXLv13,zPDXL-neg,dark-skinned male, AmoreNegative-neg, (embedding:NEGATIVE_HANDS:1.0),
Steps: 26, CFG scale: 7, Sampler: Euler a, Seed: 970580183, TI: [object Object], Size: 896x1152, Model: featurelessMixPony_v20, Version: f2.0.1v1.10.1-previous-531-g210af4f8, Module 1: sdxlfp16.vae, Model hash: fdae6ee6ad, Schedule type: Automatic,
ADetailer model: mediapipe_face_mesh_eyes_only, ADetailer version: 24.8.0, ADetailer mask blur: 4, ADetailer model 2nd: hand_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur 2nd: 4, ADetailer confidence 2nd: 0.3, ADetailer inpaint padding: 32, ADetailer dilate erode 2nd: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding 2nd: 32, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True
(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
You can never learn anything with these clickbait headlines.
I did 7 attempts at training a logo on Flux. Here are my findings.
(Kenjo) (2024)
Image description: A young woman with orange eyes and green hair styled in a side-swept bang. She is wearing a pair of thin, black-framed glasses. Her outfit consists of a dark navy blue business suit with a white button-down shirt underneath. She has a name tag with garbled text on her left lapel, and an ID card on a red lanyard around her neck. The background shows a modern urban setting with clear sky, tall, multi-story buildings on either side, and a yellow metal railing on the left side of the image. The woman is standing on a wide, concrete pathway that leads away from the viewer, with a body of water which is partially visible on the left. Her posture is leaning forward, and she is smiling with a cheerful expression.
Full Generation Parameters:
score_9, score_8_up, score_7_up, anime screencap, source_anime, 1girl, solo, <lora:Anosillus_SSSS.Dynazenon_V2:.85>, KJOanosillus, green hair, red eyes, sidelocks, single hair bun, blunt bangs, suit, pants, white collared shirt, id tag, glasses, shirt tucked in, looking at viewer, arms behind back, leaning forward, head tilt, open mouth, blush, smile, outside, bridge, city in background, (Beautiful, medium Breasts:1.2), natural breasts,
Negative prompt: score_6, score_5, score_4, monochrome, greyscale,
Steps: 30, CFG scale: 7, Sampler: Euler a, Seed: 403817189, VAE: sdxlVAE_sdxlVAE.safetensors, Size: 832x1216, Model: autismmixSDXL_autismmixConfetti, Version: f0.0.17v1.8.0rc-latest-287-g77bdb920, Model hash: ac006fdd7e, Hires steps: 14, Hires upscale: 1.25, Hires upscaler: 4x-AnimeSharp,
ADetailer model: face_yolov8n.pt, ADetailer version: 24.4.2, Denoising strength: 0.7, ADetailer mask blur: 4, ADetailer model 2nd: Eyes.pt, ADetailer model 3rd: hand_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer mask blur 2nd: 4, ADetailer mask blur 3rd: 4, ADetailer confidence 2nd: 0.3, ADetailer confidence 3rd: 0.3, ADetailer inpaint padding: 32, ADetailer dilate erode 2nd: 4, ADetailer dilate erode 3rd: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding 2nd: 32, ADetailer inpaint padding 3rd: 32, ADetailer denoising strength 2nd: 0.4, ADetailer denoising strength 3rd: 0.4, ADetailer inpaint only masked 2nd: True, ADetailer inpaint only masked 3rd: True, Clip skip: 2
(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
I don't think so. They're going to have to do a lot better than a tutorial to win people back. That said, the two Flux models being distilled making them close to impossible to fine-tune sucks too.
In this tutorial, we’ll walk you through the steps to fine-tune Stable Diffusion 3 Medium to generate high-quality, customized images.
(IndolentCat) (2024)
Image description: An old man with a stern, intense expression. He has a muscular build, and he has a full, white beard and mustache, complemented by short, silver hair that is neatly combed back. He is wearing a traditional Chinese-style outfit, a blue long-sleeved shirt with a high collar and wide sleeves, and black pants.
Full Generation Parameters:
score_9, score_8_up, score_7_up, BREAK jackie chun, fighting stance, old man, male focus, grey hair, beard, mustache, chinese clothes, black jacket,black pants,black eyes,hair slicked back, <lora:RoshiPony:1>
Negative prompt: 3d,greyscale, monochrome,watermark,own hands together, sash, waist ribbon,belt
Steps: 26, CFG scale: 6, Sampler: Euler a, Seed: 1994369863, VAE: sdxl_vae.safetensors, Size: 832x1248, Model: icat sarponyxV1, Version: f0.0.15v1.8.0rc-latest-237-g50229a05,
Mask blur: 4, Model hash: 40f11cf32a, Inpaint area: Only masked, ADetailer model: face_yolov8n.pt, Noise multiplier: 0.5, ADetailer version: 24.1.2, Denoising strength: 0.4, ADetailer mask blur: 4, Masked area padding: 32, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer inpaint padding: 32, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True
(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
(Alastor_) (2024)
Image description: An elven woman standing with straight, silver hair that, and green eyes that give her a serious expression. She is wearing a long high collar dress that is predominantly white with a deep blue stripe going down the center with gold trim. A white cape is fastened at the neck with a golden clasp that matches the trim on her dress. In the background, there is a wooden door with a simple design and to the right, there is a potted plant with green leaves and white flowers.
Full Generation Parameters:
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, source_anime, <lora:StS_PonyXL_Detail_Slider_v1.4_iteration_3:3.5>,cinematic shadow, character focus, detailed skins, soft skins, (cowboy shot:1.4), perfect curvy small breasts,dynamic pose, <lora:Elmesia_El-Ru_Sarion:1>,elmesia, pointy ears,aqua eyes, bangs,long silver hair,alternate costume, white capelet, long sleeves dress,jewelry,dress,bridal gauntlets,
Negative prompt: score_6,score_5, score_4, photo, deformed, black and white, disfigured, low contrast, muscular, censored, big, (fat:1.2), monochrome, ugly, bad anatomy , long neck, oversized limbs, long body, oversized hands,interlocked fingers,( bad face), long body, adult, realistic, people, mans,3d, child, text, twitter username, username
Steps: 30, CFG scale: 7, Sampler: Euler a, Seed: 1002580313, Size: 768x1024, Model: perfectPonyXL_v10, Version: v1.10.1, Model hash: e31a2563f0, Schedule type: Automatic,
ADetailer model: person_yolov8n-seg.pt, ADetailer version: 24.9.0, ADetailer mask blur: 4, ADetailer model 2nd: face_yolov8n.pt, ADetailer confidence: 0.3, Style Selector Style: base, ADetailer dilate erode: 4, Style Selector Enabled: True, ADetailer mask blur 2nd: 4, ADetailer confidence 2nd: 0.3, Style Selector Randomize: False, ADetailer inpaint padding: 32, ADetailer dilate erode 2nd: 4, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, ADetailer inpaint padding 2nd: 32, ADetailer denoising strength 2nd: 0.4, ADetailer inpaint only masked 2nd: True, Clip skip: 2
(andreac75) (2024)
Image description: A man riding a large, muscular beast with prominent horns and glowing blue eyes in a desert setting. The rider is wearing an orange jacket, gray pants, and has long black hair. They are traversing a sandy terrain flanked by tall rock formations.
Full Generation Parameters:
A futuristic nomad rides a massive, otherworldly beast across a barren, alien landscape. The beast has a sleek, yet organic form, with multiple limbs and glowing eyes. The nomad is dressed in flowing, layered clothing, with intricate patterns and symbols. The background features a vast, empty plain with towering rock spires and a distant, surreal horizon <lora:Adventure_Comic_Book:0.7>
Steps: 25, CFG scale: 1, Sampler: Euler, Seed: 1778656323, Size: 768x1360, Model: flux1-dev-fp8, Version: f2.0.1v1.10.1-previous-519-g44eb4ea8, Model hash: 275ef623d3, Schedule type: Simple, Distilled CFG Scale: 4, Diffusion in Low Bits: Automatic (fp16 LoRA)
(iambobokay) (2024)
Image description: A girl standing on a dirt path in a forest. She has short black hair and blue eyes. She is wearing a gray, wide-brimmed hat, a red V-neck t-shirt, a gray backpack with black straps, gray shorts with black trim and her legs are covered in black stockings.
Full Generation Parameters:
score_9, score_8_up, score_7_up, 1girl, solo, uncensored, <lora:KabanChanXL_v1.0:1> kabanchan, 1girl, solo, shy, smile, looking at viewer, black hair, blue eyes, light grey hat, red shirt, light grey shorts, black pantyhose, light grey backpack, holding strap, dutch angle, outdoors, nature, savannah, tree,
Negative prompt: score_4, score_3, score_2, score_1, ugly, bad hand, bad , watermark, signature
Steps: 30, CFG scale: 7, Sampler: Euler a, Seed: 2849070498, Size: 1024x1024, Version: v1.9.4, Model hash: 35fe8cdd71, Schedule type: Automatic,
ADetailer model: face_yolov8n.pt, ADetailer prompt: [object Object], ADetailer version: 24.8.0, ADetailer mask blur: 4, ADetailer confidence: 0.6, ADetailer dilate erode: 4, ADetailer inpaint padding: 32, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True
(UnstableGen) (2024)
Image description: A robot adorned with a long, flowing purple cloak, an oversized pointed wizard’s hat decorated with golden stars. Beneath the hat are a pair of glowing eyes, and a long white beard that reaches down to the chest area of the robot. The body of the robot is distinctly mechanical; it has articulated metal arms and hands. One hand appears to be magic emanating from its palm—a glowing orb surrounded by smaller sparks.
Full Generation Parameters:
Wizard battle droid
Steps: 25, CFG scale: 3.5, Sampler: Undefined, Size: 832x1216, extra: [object Object], Created Date: 2024-09-14T1952:04.6386361Z, Clip skip: 2
(LittleJelly) (2024)
Image description: A young woman sitting on an orange couch in a cozy, indoor setting. She has blue eyes and blonde hair styled in a high ponytail with a scrunchie. She is wearing a casual blue denim dress. In the background, there is a large window to the left, through which green foliage can be seen. To the right, a wooden bookshelf filled with various books in different colors and sizes is visible, and there are a two books stacked on the couch next to her under a cushion.
Full Generation Parameters:
score_9, <lora:SeishunButaYarou_ToyohamaNodokaXL:0.8>, 1girl, solo, closed mouth, light smile, light blush, side ponytail, blonde hair, blue eyes, parted bangs, hair scrunchie, orange scrunchie, NodokaDress, off-shoulder dress, blue dress, denim, bare shoulders, short sleeves, short dress, head tilt, thigh gap, sitting, looking at viewer, blurry background, indoors, flower, window, bookshelf Negative prompt: monochrome, censored, realistic, shaded face, hands on own hips
Steps: 30, CFG scale: 7, Sampler: Euler a, Seed: 1093750190, VAE: sdxl_vae.safetensors, Size: 832x1216, Model: snowpony_v10, Version: f1.0.2-v1.10.1RC-latest-691-g37223711, Model hash: d6f941b46b, Hires steps: 15, Hires upscale: 1.5, Schedule type: Automatic, Hires upscaler: R-ESRGAN 4x+ Anime6B,
ADetailer model: face_yolov8n.pt, ADetailer version: 24.9.0, Denoising strength: 0.3, ADetailer mask blur: 4, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer inpaint padding: 32, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, Clip skip: 2
(AIDigitalMediaAgency) (2024)
Image description: A dog sitting in front of a computer desk, attentively looking at multiple monitors displaying financial charts. The setting is an office space, illuminated by the warm glow of a wall lamp and ambient lighting, creating a focused yet cozy atmosphere.
Full Generation Parameters:
"A dog reading stock market charts and making trades on three monitors" , <lora:aidmaHyperrealism:0.45> aidmahyperrealism, <lora:aidmaMJ6.1:0.75> aidmaMJ6.1
Steps: 35, CFG scale: 1, Sampler: Euler, Seed: 2650516917, Size: 720x1280, Model: flux1-dev-bnb-nf4-v2, Version: f2.0.1v1.10.1-previous-461-g948e9145, Model hash: bea01d51bd, Schedule type: Simple, Variation seed: 1786027241, Distilled CFG Scale: 3.5, Variation seed strength: 0.65
You're good to go as long as it's original enough. If it isn't then that's just copyright infringement. You might as well have right-clicked "save as".
This show just keeps hittin'.
(GGG_666) (2024)
Image description: A young woman with brown eyes, and long, light brown hair styled in two braided pigtails. She wears a white, jumpsuit with a high collar and a small chest pocket. Her outfit is complemented by black gloves, black with white soles, and a pair of small black bags attached to her belt. She is crouching on one knee, with her other knee bent and her elbow resting on her thigh. The background features a sterile, metallic environment with blue and gray tones.
Full Generation Parameters:
<lora:Hyper-SDXL-8steps-lora:1> <lora:Fixhands_anime_bdsqlsz_V1:1> zPDXL2, score_9, score_8_up, score_7_up, source_anime, intricate details, perfect anatomy BREAK outdoors, city, tokyo, japan, audience, crowd, on one knee, hand on ground, elbow on knee, looking at viewer, Relieved, Mouth turned up slightly, eyes wide open, and a relaxed jaw., 1girl, solo, solo focus, <lora:GAGE-remi_ruth_XL(pony)v10:1> gage-remi, brown hair, low twin braids, brown eyes, glasses, gage-remi outfit, white dress, black gloves, belt pouch, white pants, black shoes,
Negative prompt: zPDXL2-neg, NEGATIVE_HANDS, low quality, bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, source_furry, source_pony, source_cartoon, blurry, AissistXL-neg,
Steps: 10, CFG scale: 1.5, Sampler: Euler a, Seed: 2003127904, VAE: sdxl-vae-fp16-fix.safetensors, ENSD: 31337, Size: 832x1216, Model: susamixPony_v20ForPony, Version: f1.1.0dev-v1.10.1RC-latest-1147-g3e80b4d8, freeu_b1: 1.01, freeu_b2: 1.02, freeu_s1: 0.99, freeu_s2: 0.95, TI hashes: [object Object], Model hash: 81721f5112, Hires upscale: 2, Schedule type: Simple, freeu_enabled: True, Hires upscaler: 4x_BooruGan_600k,
ADetailer model: face_yolov8n_v2.pt, ADetailer prompt: [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP] [SEP] [SKIP], ADetailer version: 24.9.0, Denoising strength: 0.25, ADetailer mask blur: 4, ADetailer confidence: 0.3, ADetailer dilate erode: 4, ADetailer inpaint padding: 32, ADetailer denoising strength: 0.4, ADetailer inpaint only masked: True, Clip skip: 2
(alerus1995) (2024)
Image description: A woman standing in the middle of a city street, wearing a unique dress made entirely of multiple tiny monitors, whose screens are displaying various images, with a few stray cables hanging down from the bottom of the dress.
Full Generation Parameters:
cinematic photo The image depicts a woman standing on a city street,wearing an unusual and eye-catching dress made of numerous small computer monitors. The dress is designed to resemble a building or a structure,with each monitor displaying different images and logos. The background features a bustling urban environment with buildings,shops,and pedestrians. The sky is clear,suggesting a sunny day. The overall scene combines elements of fashion and technology,creating a unique and intriguing visual.,, 35mm photograph, film, bokeh, professional, 4k, highly detailed
Negative prompt: drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly
Steps: 20, CFG scale: 1, Sampler: Euler, Seed: 3396801630, Size: 512x840, Model: flux1-dev-bnb-nf4-v2, Tiling: True, Version: f2.0.1v1.10.1-previous-495-g4f64f6da, Model hash: bea01d51bd, Hires steps: 9, Hires upscale: 2.25, Schedule type: SGM Uniform, Hires upscaler: R-ESRGAN 4x+, Denoising strength: 0.5, Distilled CFG Scale: 3.1
(JudgeNaegi) (2024)
Image description: A young woman with yellow eyes and short purple hair that curl at the ends. She is wearing a large, pointed witch hat with a wide brim. She is dressed in a black, sleeveless dress with a frilly hemline, thigh-high stockings and detached sleeves. The background shows a pink door flanked by two a small, rectangular paintings. The floor is composed of gray bricks, creating a contrast with the girl's dark attire.
Full Generation Parameters:
score_9, score_8_up, score_7_up,anime_source, source_anime, best background, detailed background, anime screencap, Blair, Witch Outfit, full body, sending kiss, blush, indoors, dynamic angle, dynamic camera, solo, <lora:JN_Blair_Soul_Eater:0.8>
Negative prompt: pubic hair, 3d, cropped, censored, bar censoring, mosaic censoring, (simple background:1.0), siblings, bad legs, clones, monochrome, clones, sketch, rought lines, patreon username, logo, bad proportions, artist signature, artist name,
Steps: 30, CFG scale: 8, Sampler: Euler a, Seed: 783882542364498, Size: 512x768, Model: autismmixSDXL_autismmixDPO, Version: ComfyUI, Model hash: d3ee23d452
(Weak_Examination) (2024)
Image description: The image depicts a city skyline with a prominent, are stylized with a neon blue glow and surrounded by numerous points of light. From the center of the image, radiant pink light beams streak towards the viewer in a symmetrical pattern, creating a dynamic sense of movement and energy.
Full Generation Parameters:
This eye-catching digital artwork features a neon-lit city skyline in wire form with a futuristic background. The black space serves as a canvas for the glowing blue and purple lights that seem to pulse along the building, giving the work a sense of movement and energy. The contrast between the illuminated areas and the dark background creates a striking visual effect and emphasizes the elegance of the skyliner. This work demonstrates the artist's ability to combine traditional art techniques with digital technology, resulting in a stunning holographic style image that captivates the viewer. , <lora:FluxDFaeTasticDetails.safetensors:0.8> <lora:glowing_flux.safetensors:0.8>,
Negative prompt: unknown
Steps: 20, CFG scale: 4, Seed: 191652213097258, Size: 832x1216, Model: FLUX, Version: ComfyUI, Model hash:
(MikadoNagi) (2024)
Image description: A girl with long black hair and brown eyes standing in a sunny field of yellow flowers. She is wearing a traditional Japanese schoolgirl outfit, which consists of a white blouse with long sleeves and a blue sailor collar, tied with a blue neckerchief. The blouse is paired with a blue pleated skirt. The girl's expression is cheerful, with a wide smile and her right hand raised to her head, adjusting her hair. The background showcases a blue sky dotted with white clouds, and a distant mountain range.
Full Generation Parameters:
1girl, solo, (field:1.2), (blue sky:1.2), smile, (cowboy shot, dynamic pose:1.4), yuzuki_kaede, brown eyes, black hair, long hair, bangs, school uniform, serafuku, white shirt, long sleeves, blue skirt,, <lora:yuzuki_kaede_pony_ver1:0.8>, score_9, score_8_up, score_7_up, source_anime, best quality, uncensored, rating_safe,
Negative prompt: teeth, stadium,, rating_explicit, nsfw, low quality , bad anatomy, bad proportions, extra legs, deformed anatomy, messy color, deformed fingers, bad, distracted, hyperrealistic, source_furry, source_pony, source_cartoon, ribs, NEGATIVE_HANDS, three fingers, four fingers, six fingers, seven fingers, extra fingers, missing fingers, fused fingers, deformed fingers, ugly fingers, deformed hands, bad hands, worst time, worst hands, wrong hands, twisted hands, ugly hands, deformed toes, fused toes, missing toes, wrong feet, deformed feet, ugly feet
Steps: 25, CFG scale: 7, Sampler: Euler a, Seed: 3595452465, ENSD: 31337, Size: 832x1216, Model: 3x3x3mixxl_v02_vae, Version: v1.10.0, Emphasis: No norm, TI hashes: [object Object], Model hash: a213e00378, Hires steps: 10, Hires upscale: 1.25, Schedule type: Automatic, Hires upscaler: 4x-UltraSharp, Denoising strength: 0.4, Clip skip: 2
(davinch1111) (2024)
Image description: A striking blue cat sitting in a snowy environment. The cat’s fur appears to be made of ice, with intricate ice formations growing out from its coat, and it has bright green eyes that stand out against the blue fur.
Full Generation Parameters:
"Create a photorealistic image of a swirling gust of ice and snow that fills the air, with a majestic cat silhouette forming at the center. The ice and snow are rendered in exquisite detail, with delicate, crystalline structures and intricate patterns that shimmer and shine like a thousand tiny diamonds. The cat's eyes are bowls of gemstones, with a kaleidoscope of colors and facets that seem to shift and change as the viewer looks. The gemstones are rendered in precise detail, with subtle imperfections and inclusions that add to their realism. The overall effect is one of magical, wintry wonder, as if the ice and snow are alive and taking shape before the viewer's eyes. The image should capture the dynamic, swirling energy of the snow and ice, with a sense of movement and flow." Highest-Quality, 4k, intricate details, visually stunning, Masterpiece
Steps: 20, CFG scale: 3.5, Sampler: Undefined, Seed: 4294967298, Size: 832x1216, extra: [object Object], Created Date: 2024-09-12T0456:58.8170592Z, Clip skip: 2
Or just not show people what you're typing.
The limitations of the PC98 make for an aesthetic that is truly special.
*zip*
Wait a minute. I need some context for the text.
Gotta imagine his foot's around the other side, along with the rest of that coat.
Art isn't work, it's speech. It's part of the human condition. Art is useless, said Wilde. Art is for art’s sake—that is, for beauty’s sake.