Model
Trends
.ai
Model
Trends
.ai
model AI sumber terbuka terbaik
Jalankan secara tempatan
EasyFix.safetensors
41 MB · SafeTensor
Muat turun disediakan oleh Civitai. Sesetengah pencipta memerlukan log masuk Civitai dahulu.
AD
<easyfix-xl>
Tentang model ini
STABLE DIFFUSION XL 1.0 · LoRA
Dicipta oleh
adempotent
di Civitai
Despite the easyfix name, using this lora is actually complicated. It's a negative which according to the documentation wants both the overfit token as both as positive and a negative with weights of up to ten, however seems to produce beneficial results as a positive as well. Check the info link for samples
Nota pencipta
Put in your negative prompt: (overfit style:1.0) EasyFix is a negative LoRA trained on AI generated images from CivitAI that show extreme overfitting. This LoRA improves generated image quality without any major stylistic changes for any SDXL model. Suggested Strength: 1 to 16 Important: adjust the strength of (overfit style:1.0) more than the strength of the LoRA What is overfitting? According to IBM (source: ), "Overfitting is a concept in data science, which occurs when a statistical model fits exactly against its training data. When this happens, the algorithm unfortunately cannot perform accurately against unseen data, defeating its purpose. Generalization of a model to new data is ultimately what allows us to use machine learning algorithms every day to make predictions and classify data." What does overfitting look like in Stable Diffusion? Repeating patterns, nonsensical details, small dots, strange artifacts, facial blemishes... etcetera. If you look at an AI generated image and see some strange details that don't make sense, the chances are high that the image shows signs of overfitting. Overfitting as an Aesthetic Aesthetic appeal is subjective, so if you enjoy the incredibly detailed images Stable Diffusion is good at making, don't view this model as an attack on your personal taste! Please do an A/B comparison using EasyFix and judge for yourself which is better. Avoiding Overfitting In Image Generation: Simpler prompts, with minimal negative prompting. If needed, lower CFG scale. In Training: I will eventually be writing a short guide for advanced users on how I train my LoRA, so watch this space. AI_Characters has an excellent guide on training methodology (see: "Evaluating your model") Methodology Collect tagged AI-generated images from CivitAI that show overfitting (using ). Images should be greater than minimum size of 768x768. Remove all brackets and attention strength from captions. (e.g. "((cute dog:4))" becomes "cute dog"). Remove all tags relating to quality (e.g. "masterpiece, best quality, insanely detailed"). Add a trigger word at the start of each word like "overfit style". Train on the images and generate A/B comparison images while training to save time later.
Kata pencetus
overfit style
(overfit style:2.0)
(overfit style:4.0)
<PUT OVERFIT STYLE IN NEGATIVE PROMPT>
8,294 muat turun · 719 suka di Civitai
SHA256
A85BDF62BC95C69C52DCA7D40559DFCE928D6DDDD339CA51735021B34E4D573F
ID Model ModelTrends.ai
#19998
Laporkan kandungan
Contoh render
Prompt dan tetapan yang dikongsi oleh orang yang membuat render ini di Civitai. Pilih render untuk melihat cara ia dibuat.
Tetapan
Sampler
DPM++ 2M Karras
Langkah
48
Guidance
5
Seed
1584292402
Saiz
832x1216
Clip skip
1
Berat yang digunakan
1
Prompt
artwork of a {An enchanting image featuring an adorable kitten necromancer wearing intricate ancient robes, holding an ancient staff, hard at work in her fantastical workshop, intricate runic symbols swirling around her, it's clear that she's busy casting a powerful spell. Her fluffy tail sways gently as she concentrates on the task at hand, adding to the whimsical atmosphere of this magical scene. The soft lighting and detailed surroundings create an immersive environment where imagination runs wild. This charming artwork is sure to delight fans of both kittens and fantasy worlds alike, transporting them into a realm filled with wonder and possibility, by (artem demura:1.36)}, by (artem demura:1.36), detailed background, masterpice, trending on artstation, best quality, 4k textures, ultra detailed
Prompt negatif
Asian, black skin, frame, 3d, render, photo, nipples, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry, (worst quality, low quality, normal quality:2)
Tetapan
Sampler
Euler a
Langkah
48
Guidance
5
Seed
350169140
Saiz
832x1216
Clip skip
2
Berat yang digunakan
0.7
Prompt
Realism_Quality_2xx_By_Stable_Yogi, 1girl, long wavy hair, blonde hair, blue eyes, gentle smile, long eyelashes, eyeliner, red lips, makeup,ValentinesDateSDXL, red dress, date_pov, across table, sitting, valentine, roses, wine, diner, night, candles, (romantic:1.4), (floating hearts:2.1), fully dressed, closed dress, high collar dress, Victorian dress, Victorian style, Victorian age.
Prompt negatif
realisticvision-negative-embedding, score_6, score_5, score_4, worst quality, low quality, text, censored, deformed, bad hand, blurry, (watermark), weights, extra hands, extra dicks, 3 finger, 5 finger, bangs, bad anatomy, big head, artist signature, artist name. 25 years old or younger, child, adolescent, 16-token-negative-deliberate. epiCNegative, epiCPhotoGasm-colorfulPhoto, overfit style, (overfit style:2.0), (cleavage:1.4), naked skin, fcNeg.
Tetapan
Sampler
Heun
Langkah
42
Guidance
2.5
Seed
1347843765
Saiz
832x1216
Clip skip
2
Berat yang digunakan
0.75
Prompt
V for Vendetta, Dark Atmosphere, CloseUp, ergo Proxy Diving down, sideview, minimal, simple colors, 70s, stylish, bright, high contrast, postapocalyptic, very detailed, hd
Prompt negatif
male, signature, ahegao face, (worst quality, low quality:1.4), fcNeg , (fluorescence:1.4) , simple , out fraMe,, EasyNegative, hermaphrodite, cropped, not in the frame, additional faces, jpeg large artifacts, jpeg small artifacts, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, not finished drawing, unfinished image, bad eyes, doll, 3d, cartoon, (bad eyes:1.2), (worst quality:1.2), (low quality:1.2), bad-image-v2-39000, (bad_prompt_version2:0.8)
Tetapan
Sampler
Heun
Langkah
42
Guidance
2.5
Seed
1347843766
Saiz
832x1216
Clip skip
2
Berat yang digunakan
0.75
Prompt
V for Vendetta, Dark Atmosphere, CloseUp, ergo Proxy Diving down, sideview, minimal, simple colors, 70s, stylish, bright, high contrast, postapocalyptic, very detailed, hd
Prompt negatif
male, signature, ahegao face, (worst quality, low quality:1.4), fcNeg , (fluorescence:1.4) , simple , out fraMe,, EasyNegative, hermaphrodite, cropped, not in the frame, additional faces, jpeg large artifacts, jpeg small artifacts, ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, disfigured, deformed, body out of frame, blurry, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, not finished drawing, unfinished image, bad eyes, doll, 3d, cartoon, (bad eyes:1.2), (worst quality:1.2), (low quality:1.2), bad-image-v2-39000, (bad_prompt_version2:0.8)
Tetapan
Sampler
DPM++ 2M Karras
Langkah
35
Guidance
10
Seed
159168918
Saiz
832x1216
Clip skip
2
Berat yang digunakan
1
Prompt
ng_deepnegative_v1_75t easynegative, EasyNegativeV2, haganef, anime, 1GIRL, solo, sexy body, big breasts, thicc breasts, thicc butt, BIGGER CHEST, oriana rose, long hair, blonde hair, yellow eyes, drill hair, bangs, blunt bangs ,BLACK BODYSUIT, BODYSTOCKING, BLACK PANTS, BLACK GLOVES, GOLD TRIM, smile seduce, make up, corset, tall about 180 cm, sexy body.
Prompt negatif
plastic, Deformed, blurry, bad anatomy, bad eyes, crossed eyes, disfigured, poorly drawn face, mutation, mutated, extra limb, ugly, poorly drawn hands, missing limb, blurry, floating limbs, disconnected limbs, malformed hands, blur, out of focus, long neck, long body, ((((mutated hands and fingers)))), (((out of frame))), (((signature))), (((signatures))) blender, doll, cropped, low-res, close-up, poorly-drawn face, out of frame double, two heads, blurred, ugly, disfigured, too many fingers, deformed, repetitive, black and white, grainy, extra limbs, bad anatomy,
Tetapan
Sampler
LCM
Langkah
8
Guidance
1
Saiz
2965x2965
Prompt
<ohsoliveperformer>Dangerous young punk woman on stage. Large bodybuilder drummer behind her. Kaleidoscopic colorful lighs, shadows. Smoke. Darkness. Slim and very fit. Playing her electric 6-strings (guitar:1.5), wearing leather pants and a crop top. SFW. Detailed hands. Text in both the drum kit and the girl's t-shirt reads "Buzzrs", which is the name of her band, with a yellow lightning bolt icon.
Tetapan
Sampler
Euler a
Langkah
25
Guidance
3.5
Seed
510113582
Saiz
1024x1024
Clip skip
2
Berat yang digunakan
1
Prompt
Masterpiece, solo, female, 1girl, best quality, perfect quality, amazing quality, score_9, score_8_up, score_7_up, Luz Noceda, brown hair, short hair, brown eyes, dark skin, uniform, multi color sleeves, multi color leggings, gray tunic, dark gray belt, cowl, white loafer sneakers, thick thighs, thick thighs, wide hips+++, female+++, female only+++, female focus+++, by hanuvo, looking at viewer lovingly, presenting ass, ass focus+++, huge ass, clothed ass++++, covered ass, massive thighs, bottomheavy, big ass, huge ass, gigantic ass, thick thighs, massive thighs, easynegative,
Prompt negatif
(overfit style:4.0), nsfw, bad anatomy, muscular, naked, nude, 3d, panel, multi, (deformed), shorts, mutation, multi limb, (amputee), (signature), logo, (worst quality, poor quality:1.3), skinny, cross-eyed, poorly drawn, poorly drawn hands, watermark, deformed, blurry, (bad anatomy), (disfigured), poorly drawn face, mutation, mutated, extra limb, ugly, out of focus, depth of field, focal blur, watermark, sketch, (low quality, worst quality:1.4), (bad anatomy),(inaccurate limb:1.2), bad composition, inaccurate eyes, extra digit, fewer digits, (extra arms:1.2), bad feet, bad finger, bad nails, cropped legs, bad-hands-5, (easynegative:1.3), (deformed iris, deformed pupils, black and white, red eyes, retro artstyle, clone, cloning, head facing wrong way, monotone, (overfit style:2.0), bad proportions,
Tetapan
Sampler
Euler
Langkah
28
Guidance
5
Saiz
1224x2048
Prompt
1man, solo, cowboy shot, depth of field, (masterpiece), [quasarcake], best quality, fantasy setting, dark ruins background, goat anthro, humanoid demon goat, red eyes, horizontal_pupils, sharp claws, big horns, lean body type, adult and mature appearance, (mature face), calm expression, black and purple mage robes, silver accents on the clothes, intricate leather ornaments, silver necklace, silver bracelets, holding a mage staff, casual pose, looking to the side, gloomy, dark, colourful, vibrant colours, dynamic lighting, dynamic composition, detailed background, UHD, (amazing quality:1.5)
Prompt negatif
lowres, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest, censored, bar_censor, (pregnant), chibi, loli, young, child, kid, teen, teenager, text, text on clothes, conjoined, futanari, bad eyes, mosaic_censor, sweat, robot, mechanical, nsfw
Model AI untuk penjanaan imej, video dan teks
easyfix xl ialah LoRA untuk keluarga Stable Diffusion XL 1.0 yang disenaraikan di ModelTrends.ai, katalog baca sahaja untuk model AI imej, video dan teks sumber terbuka. Bandingkannya dengan model Stable Diffusion XL 1.0 lain, semak skor habanya untuk melihat trendnya, dan bukanya di PirateDiffusion atau BitVector untuk mencubanya.
Layari mengikut keluarga model
Layari semua model