Model
Trends
.ai
Model
Trends
.ai
i migliori modelli di IA open source
Esegui in locale
aniverseXL_v20.safetensors
6.46 GB · SafeTensor · fp16 · pruned
I download sono forniti da Civitai. Alcuni creatori richiedono prima l'accesso a Civitai.
AD
Installa / Esegui su Graydient
Richiede un abbonamento
<aniverse2-xl>
Informazioni su questo modello
STABLE DIFFUSION XL 1.0 · Modelli base
Creato da
Samael1976
su Civitai
by Samael1976 - A traditional SDXL base model for creating portraits. Excels at high contrast, almost anime-like realism
Note del creatore
!!! UPLOADING/SHARING MY MODELS OUTSIDE CIVITAI IS STRICLY PROHIBITED* !!! Check my EXCLUSIVE models on : • • • • SDXL - Pony: • • • • SD1.5: • • • • • Also in Collaboration with This model is free for personal use and free for personal merging(*). For commercial use, please be sure to (Ko-fi) or by email: samuele[dot]bonzio[at]gmail[dot]com ⬇Read the info below to get the high quality images (click on show more)⬇ Aniverse XL - make the impossible possible! This is a long shot project, I’d like to implement something new at every update! The name is a merge of the two words: Animation and Universe (and a word pun: Any+Universe -> Anyverse -> Aniverse) -> If you are satisfied using my model, press on ❤️ to follow the progress and consider leaving me ⭐⭐⭐⭐⭐ on model review, it's really important to me! Thank you in advance 🙇 And remember to publish your creations using this model! I’d really love to see what your imagination can do! Recommended Settings: - Excessive negative prompt can makes your creations worse, so follow my suggestions below! - Before applying a LoRA to produce your favorite character, try it without first. You might be surprised what this model can do! VERSION 3 AND LATER: - Clip skip: 2 - Width: 768 - Height: 1344 - CFG: 5.5 - Steps: 30 - Sampling: DPM++ 2M o Euler Max - Scheduler: Karras - Trigger Word: 4n1v3rs3 EXAMPLE OF GENERAL PROMPT:   POSITIVE: (Type of Shoot), (Subject), adult, the description, (background), more details, depth of field, dynamic angle, fashion photography, sharp, hyperdetailed:1.15, 4n1v3rs3   EXAMPLE: Portrait, Zelda, adult, cute, seductive, innocent, light smile:0.3, plump lips, slender body, ankle-length pink dress, jeweled tiara, golden shoulder pads, a gold chain as a necklace, vibrant, fantasy, epic, heroic, cave background, depth of field, dynamic angle, fashion photography, sharp, hyperdetailed:1.15, 4n1v3rs3   NEGATIVE: worst quality:1.4, low quality:1.4, front light, grayscale, ugly, fat, wide hips, curvy, child, young, kid, bad hands, interlocked fingers, extra finger, missing finger, fused fingers, bad anatomy - creates a bit of problems with the hands - heavily retouches the "creativity" of the image. - Also in long focal lengths (full body shot) the faces do not render as well as they should - it is more adherent to the original image and works very well. - Although it tends to gloss over images a bit too much and make them look flat, and removes a little bit of details. - it tends to make faces a little too rounded (for my taste) - It works much better with Euler Max than DPM++2M - Perfect for making male figures About SAMPLERS with Karras like SCHEDULER: - DPM++2M: this is my favorite, both for colors and details, it makes the image more towards 2.5D, great for portraits and cowboy shots. - Euler Max: It has less details, but it renders better at the face level when using the "full body shot" prompt and tends to have a greater proximity to 2D. You decide what to choose based on your needs. VERSION 1 AND 2: - VAE: a special VAE is already included, you don't need it - (Thanx to ) - Clip skip: 2 - Upscaler:  or - Width: 720 (o 768) - (probably more, but I've not tested) - Height: 1280 - (probably more, but I've not tested) - CFG Scale: 3~7 - Steps: 20~30 (also, I've not tested so much) - For 2D (or very close to 2D) - - CFG: 6 - Steps: 20 - Sampling favorite method: Restart - Scheduler: Polyexponential or SGM Uniform - Embedding to use: + (in positive prompt) + , (in negative prompt) maybe the best - Sampling alternative favorite method: Euler a - Embedding to use: + , EXAMPLE OF GENERAL PROMPT - POSITIVE PROMPT: 4n1v3rs3, (Style of the image), your subject, the description, (background), more details EXAMPLE: 4n1v3rs3, (Oil Painting), woman, wearing red dress, (sunrise background), masterpiece, high details... (ect, ect) - NEGATIVE PROMPT: , , moles, freckles, ugly, artifacts - For 2.5D - - CFG: 6 - Steps: 20 - Sampling favorite method: DPM++ 2M or Euler_max - Scheduler: Polyexponential - Embedding to use: + (in positive prompt) + , , moles, freckles, ugly, artifacts" EXAMPLE OF MY GENERAL PROMPT - POSITIVE PROMPT: 4n1v3rs3, (Style of the image), your subject, the description, (background), more details EXAMPLE: 4n1v3rs3, (Anime 2.5D style), Rei Ayanami, wearing white EVA bodysuit, (sunrise background), masterpiece, high details... (ect, ect) - NEGATIVE PROMPT: , , moles, freckles, ugly, artifacts - For 3D - Realism - see this comparison posts: - - - - - CFG: 2.5~7 - Steps: 20 - Sampler (1): DPM++ 2M - Sampler (2): DPM++ SDE (the best for realism, but very slow generation) - Sampler (3): Euler_max - Sampler (4): UniPC - Scheduler: SGM Uniform or Polyexponential - Embeddings to use: + (in positive prompt) + , EXAMPLE PROMPT FOR REALISM: - POSITIVE: 4n1v3rs3, , (Style of the image), your subject, the description, (background), more details EXAMPLE: 4n1v3rs3, (Analog photo by Rutkowski), (Hindu young man), 25 years old, (elaborate ancient Hindu temple ruins background), (midnight hour, high quality, film grain), focus on orange and green - NEGATIVE: , moles, freckles, ugly, artifacts - MORE INFO (full prompt info): you can see all the setting I used, and choose your CFG Scale - Using Turbo or Lightning - - CFG: 2.5~3.5 - Clipskip: 2~3 - Lora to use: - Sampling method: dpm 2 turbo - Embeddings to use: + (in positive prompt) + , AVOID THIS COMBINATION: (Euler a + Uniform) - (Euler_max + SGM Uniform) - (DPM++ 3M SDE + Exponential) - (DPM++ 2M SDE + Exponential) DOWNLOAD ALL THE EMBEDDING AND LORA THAT I USED: - (put in your negative prompt) - (put in your positive prompt) - Add Details: (in positive prompt) - Pony PDXL Negative Embeddings: - Pony PDXL Negative Embeddings: - LoRA lightning: A1111 my settings: I run my Home PC A1111 with this setting: - set COMMANDLINE_ARGS= --xformers --skip-torch-cuda-test --no-half-vae (if you have low VRam, t
2,670 download · 224 mi piace su Civitai
SHA256
D05FCA080C12CDF7F60C1A1D4F1D0EA6AAED31DF953C38466115F3D93CCCFB73
ID modello ModelTrends.ai
#14491
Segnala contenuto
Render di esempio
Prompt e impostazioni condivisi da chi ha realizzato questi render su Civitai. Scegli un render per vedere come è stato fatto.
Impostazioni
Sampler
Euler_Max
Passi
20
Guidance
7
Seed
3570294098
Dimensioni
512x512
Prompt
<lora:Tsumugi_Shirogane_SDXL:1>, zPDXL2, 4n1v3rs3, (2D anime), This anime screencap is from Danganronpa the Animation. Tsumugi Shirogane wearing her uniform from Danganronpa V3. Tsumugi Shirogane has knee-length dark teal-blue hair parted in the center which is straight and smooth at the base and gradually splits into waves near the tips. Her eyes are large, round, and are a soft teal-green color. Tsumugi wears round, rimless glasses with white temples. Tsumugi's Danganronpa V3 school uniform consists of a white blouse with an orange bow tied at her collar underneath a two-button, pocketed, teal-black school blazer adorned with two silver buttons on each lapel and a single button on each gorge. She wears a knee-length teal-black pleated skirt with two dark teal stripes lining the hem. Her legwear consists of dark navy knee-length socks and teal-gray loafers. Tsumugi is in the woods, sitting on a log. She's looking at a large beetle that's next to her. Tsumugi looks wistful, nostalgic, and sad. She's crying, even with a smile on her face. A battered and worn bug box is on her lap.
Prompt negativo
unaestheticXL_bp5, zPDXL2-neg, moles, freckles, ugly, artifacts, empty background, plain background, single color background
Impostazioni
Sampler
DPM++ 3M SDE
Passi
30
Guidance
5
Seed
3607235060
Dimensioni
1280x1920
Prompt
the most beautiful landscape, fantasy, ((very detailed)), sharp focus, sharp background, best quality, valley, meadow, fountain, peasant village, stunning nature environment, (bright sunny sky), high contrast, cinematic (lights), backlight, shadows, lens flare, vibrant colors, colorful, Forest Green flowers and leaves, <lora:add-detail-xl:1> <lora:Better Blur Control:1>
Prompt negativo
blurry background, deep of field, (blurry), out of focus, undetailed, (worst quality, low quality, normal quality:2), saturated colors
Impostazioni
Sampler
DPM++ 3M SDE
Passi
30
Guidance
5
Seed
1255334752
Dimensioni
1280x1920
Prompt
the most beautiful landscape, fantasy, ((very detailed)), sharp focus, sharp background, best quality, valley, meadow, fountain, peasant village, stunning nature environment, (bright sunny sky), high contrast, cinematic (lights), backlight, shadows, lens flare, vibrant colors, colorful, Steel Gray flowers and leaves, <lora:add-detail-xl:1> <lora:Better Blur Control:1>
Prompt negativo
blurry background, deep of field, (blurry), out of focus, undetailed, (worst quality, low quality, normal quality:2), saturated colors
Impostazioni
Sampler
DPM++ 2M
Passi
20
Guidance
6
Seed
697115183
Dimensioni
768x1280
Clip skip
2
Prompt
4n1v3rs3, zPDXL2, (ultra realistic photo), (fashion photography), skinny fashion cute italian model, (Asuka Langley cosplay), red evangelion bodysuit, parted lips, full lips, softlight passing through hair, (sunset lake background), dynamic angle, best quality, highly detailed
Prompt negativo
unaestheticXL_bp5, zPDXL2-neg, moles, freckles, ugly, artifacts
Impostazioni
Sampler
DPM++ 2M
Passi
20
Guidance
7
Seed
1064149994
Dimensioni
1216x832
Prompt
(((solo))), masterpiece, best quality, very aesthetic, modern, modern anime, anime style, newest, absurdres, highres, zPDXL2 , SimplePositiveXLv2 , more details, three-quarter view , loving expression , <lora:Toko_Fukawa_SDXL:1>, This is an anime screencap from Danganronpa 3. Toko Fukawa has a disappointed expression . Toko Fukawa is enacting a side-step amid The person stands in a dense forest where the sunlight is breaking out of the clouds in the foggy red sky. The light is soft and golden, and the trees are silhouetted against it. There is a dead tree in the center of the image, with branches reaching up towards the sky. The air is thick with moisture, giving the scene a mysterious feel. There is a small stream running through the forest in the foreground. The leaves of the trees are all a soft green color, except for some in the foreground that are starting to change to a deep red color, almost brown. The ground is covered in fallen leaves. The whole scene is quiet and peaceful and seems as if a light mist has settled around the forest. Toko Fukawa wearing her uniform from Danganronpa 1. She has long dark purple hair in two braids, gray eyes and large round glasses. Her large, dark grey glasses are slightly crooked at an angle. Her uniform is a dark purple Japanese school uniform. The uniform has long sleeves, a collared shirt with a red ribbon and a long skirt with the school crest on the upper left sleeve. A red ribbon is tied around the collar of her shirt.
Prompt negativo
lowres, worst quality, low quality, bad anatomy, bad proportions, extra limbs, extra digit, extra legs, extra legs and arms, disfigured, missing arms, too many fingers, fused fingers, missing fingers, unclear eyes, username, simple background, unaestheticXL_bp5, zPDXL2-neg, moles, freckles, ugly, artifacts
Impostazioni
Sampler
DPM++ 2M
Passi
20
Guidance
7
Seed
182786631
Dimensioni
832x1216
Clip skip
2
Prompt
high quality, vibrant and detailed anime illustration, 1980s style, 1girl, long dark hair, large expressive eyes, elegant smile, wearing a luxurious space suit, pearl white with gold trim, graceful pose, standing with one hand on the hip and the other holding a laser gun elegantly by the side, poised as if preparing for a formal event, bold colors, classic Japanese anime aesthetics, retro design elements <lora:add-detail-xl:2>
Prompt negativo
lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract], negativeXL_D
Impostazioni
Sampler
Euler a
Passi
25
Guidance
7
Seed
2234391984
Dimensioni
832x1280
Clip skip
2
Prompt
score_9,score_8_up,score_7_up,score_6_up,<lora:Dreamyvibes artstyle SDXL - Trigger with dreamyvibes artstyle:0.8>,Dreamyvibes Artstyle,<lora:Psychedelic_Stylized:0.8>,<lora:Western_Comic_Art_Style_PONY_XL_by_UOC:0.8>,w3st3rnc0m1c,westerncomic,western comic art style,1girl,sexy elf,dungeon background,focus from above,sweat,naughty,A highly Create an amazing image of the famous vinh ha Long Bay in Vietnam, View towards the Bay, daylight, vivid colors, bright, amazing landscape, perfect composition, a rich and complex image of nature, a vibrant tissue of hues and textures captured digitally, best quality, double exposure, realistic, captivating, fantastical, splash art, intricately detailed, hyper detailed, maximalist style, photorealistic, concept art, sharp focus, harmony, serenity, calm, mysterious glow, dynamic lighting, masterpiece, superb composition, finest details, highest aesthetics, strong muted highlighter of fantastical waterfall surrounded by green jungle, ((view from above)), aerial photo from above as if a bird had taken the picture, mystical glow, best quality, sharp focus, high contrast, stylized, clear, colorful, ultra quality, 8k, best quality, masterpiece,midjourneyv6.1
Prompt negativo
score_5,score_4,blurry,ugly face,bad anatomy,mutated hands,low res,blurry face,bad hands,wrong hand,bad fingers,wrong fingers,extra fingers, neghands-neg_xl,ImgFixerPre0.3_xl,zPDXL2-neg,zPDXL3_xl,
Impostazioni
Sampler
Euler a
Passi
25
Guidance
7
Seed
2234391986
Dimensioni
832x1280
Clip skip
2
Prompt
score_9,score_8_up,score_7_up,score_6_up,<lora:Dreamyvibes artstyle SDXL - Trigger with dreamyvibes artstyle:0.8>,Dreamyvibes Artstyle,<lora:Psychedelic_Stylized:0.8>,<lora:Western_Comic_Art_Style_PONY_XL_by_UOC:0.8>,w3st3rnc0m1c,westerncomic,western comic art style,1girl,sexy elf,dungeon background,focus from above,sweat,naughty,A highly Create an amazing image of the famous vinh ha Long Bay in Vietnam, View towards the Bay, daylight, vivid colors, bright, amazing landscape, perfect composition, a rich and complex image of nature, a vibrant tissue of hues and textures captured digitally, best quality, double exposure, realistic, captivating, fantastical, splash art, intricately detailed, hyper detailed, maximalist style, photorealistic, concept art, sharp focus, harmony, serenity, calm, mysterious glow, dynamic lighting, masterpiece, superb composition, finest details, highest aesthetics, strong muted highlighter of fantastical waterfall surrounded by green jungle, ((view from above)), aerial photo from above as if a bird had taken the picture, mystical glow, best quality, sharp focus, high contrast, stylized, clear, colorful, ultra quality, 8k, best quality, masterpiece,midjourneyv6.1
Prompt negativo
score_5,score_4,blurry,ugly face,bad anatomy,mutated hands,low res,blurry face,bad hands,wrong hand,bad fingers,wrong fingers,extra fingers, neghands-neg_xl,ImgFixerPre0.3_xl,zPDXL2-neg,zPDXL3_xl,
Modelli di IA per generare immagini, video e testo
aniverse2 xl è un modello base per la famiglia Stable Diffusion XL 1.0 presente su ModelTrends.ai, un catalogo in sola lettura di modelli di IA open source per immagini, video e testo. Confrontalo con gli altri modelli Stable Diffusion XL 1.0, controlla il punteggio di calore per vedere la tendenza e aprilo su PirateDiffusion o BitVector per provarlo.
Sfoglia per famiglia di modelli
Sfoglia tutti i modelli