Model
Trends
.ai
Model
Trends
.ai
ang pinakamahuhusay na open source AI model
Patakbuhin nang lokal
unnamedixlRealisticModel_v7.safetensors
6.46 GB · SafeTensor · fp16
Ang mga download ay mula sa Civitai. May mga gumawa na humihingi muna ng Civitai login.
AD
I-install / Patakbuhin sa Graydient
Nangangailangan ng membership
<unnamed-ixl4-xl>
Tungkol sa model na ito
STABLE DIFFUSION XL 1.0 · Mga base model
Ginawa ni
n_Arno
sa Civitai
Recommended 40 steps at 6 guidance
Mga tala ng gumawa
UnNamed IXL V7! After listening to the active users of UnNamedIXL, here is an update that should fix some issues with V6 while keeping the dynamism brought by it (V7 will replace V6 at next auction). Special thanks to several heavy users/testers of UnNamedIXL V5! - - - - - - - - - - - In order to make it look like what was expected by these power users, i leveraged some pictures from UnNamedIXL V5 public gallery to create a dataset. This dataset was used to create 2 LoRAs: - UnNamed 5 to 7 - UnNamed 6 to 7 Both these LoRAs allowed V5 and V6 to get closer to an ideal V7 (internal models u7-5 and u7-6, with the LoRAs merged at 0.8) which were then merged together to get V7 (NuSlerp 7-5 + 7-6 at 0.4). Skin and facial features should feel more natural with this version while being more dynamic / less static. V8 will probably a "Krea2" upgrade of V7 (dataset made with V7, img2img using Krea2) in order to get better hands, but is not scheduled for now, i'll see after some external tests. Thanks for reading! Warning feedback This is exactly the kind of honest feedback i love to receive. So, for anyone looking for this info, here it is: Unamed v5 is superior to v6. v6 tends to distort into skin plasticity and weird mannequin features. If anyone also experience this kind of stuff, feel free to DM or comment in order for me to get better results in the future Return(Tensor): if a.isfinite().all(): return a else: return b base = sdm.model("UnNamedIXL_V3.9.safetensors") src = sdm.model("mine\\UnNamedIXL\\UnNamedIXL_V3.fp16.safetensors") ill = sdm.model("base\\illustriousXLV20_v20Stable.safetensors") lora = sdm.model("..\\loras\\UnNamedSpice.safetensors") l = sdm.convert(lora, base) a = sdm.add_difference(base, l, alpha=0.1) b = fix_nan(src,ill) blocks = { "BASE": 0.5, "IN00": 0.0, "IN01": 0.0, "IN02": 0.0, "IN03": 0.0, "IN04": 0.0, "IN05": 0.0, "IN06": 0.0, "IN07": 0.0, "IN08": 0.0, "M00": 0.5, "OUT00": 0.0, "OUT01": 0.0, "OUT02": 0.0, "OUT03": 0.0, "OUT04": 0.0, "OUT05": 0.0, "OUT06": 0.0, "OUT07": 0.0, "OUT08": 0.0, "VAE": 0.0, } blocks = sdm.convert(blocks,b) blocks = blocks | 0.0 c = sdm.slerp(a,b, alpha=blocks) sdm.merge(c,output="test.safetensors") V3 I didn't want to stray too far from what made V2 a different realistic checkpoint, but i still wanted to give it a small lifting. I'll use this as a base for a future V4 ;-) V3 + DMD2 Since i am going to play a bit with the , i have integrated it in UnNamedIXL V3. This version is really experimental, prefer V3 if you want to do a classic realistic image as usual. Otherwise, this version is better used as a "refiner" or "Hires.Fix" model switch leveraging an other model to give a realistic boost on other composition. Here is an example of Hires.Fix using this version and both DMD2 version of and : (click on show more for the rest of the story 😁) Simply use Euler A, CFG 1, 8 steps in both standard and Hires.Fix run but switch to UnNamedIXL V3_DMD2 during Hires. You can also try other models for the base pictures as usual and do img2img only. Here is a base picture using WAI14 (30 steps, CFG 5): And the img2img, CFG1, 8steps, 0.4 denoise, x1.5 resize: Previously Brand new V2 is a full realistic model! Build from scratch using: - Perfection Realistic [ILXL / Illustrious XL]: - PornMaster-Pro 色情大师- Illustrious & noob: - RealismHarem: - And a tiny bit of JedPointReal: It then received the "" before some precise MBW with UnNamedIXL V1 to get its composition more to my liking :D Usage: - DPM++ 2M SDE Heun + SGM Uniform - 40 steps - CFG > 6 is prefered, but feel free to experiment - Positive prompt: Can handle NLP 🎉 - Negative prompt: whatever suit your fancy, just be aware that Illustrious generate "young" characters - - Stable_Yogis_Illustrious_Negatives - A mix of If you prefere "semi-realistic" bordering on realistic, V1 is still your best bet :D V1: An "almost" realistic checkpoint, because pure realistic models feels too uncanny for me yet. Long Story™ First, special thanks to who gave me the idea and the base for this model. The release of and my tests (and the associated message received) gave me the hint that merging a bit of my other checkpoints into it could be a way to "cure" a real realistic model to better fit my current mood. The merge started as a CosineB merge of RealismHarem into . Then, i added + + + to get a specific style to the picture. But since i threaded too much outside of the realistic feel i wanted, I redid a merge with the previous checkpoint before integrating a bit of . Afterward, got in the mix at small dose and step by step, on the course of 9 Release Candidates, i smoothed the result but adding and substracting RealismHarem and some of my checkpoints at block level until i got what i wanted. Thanks for reading! 💖 Update for the more curious, some intermediary steps: V0 RC1 RC4 RC4 vs RC5 vs RC6 CuteIXL vs HoJ vs RC6 vs V1
Mga trigger word
realistic
2,529 download · 126 like sa Civitai
SHA256
5DE851376608D77AC5FCA529BA727897860D187AD66108DD15DA3C800CBD1A2F
ModelTrends.ai Model ID
#20881
I-flag ang nilalaman
Mga halimbawang render
Mga prompt at setting na ibinahagi ng mga gumawa ng mga render na ito sa Civitai. Pumili ng render para makita kung paano ito ginawa.
Mga setting
Sampler
DPM++ 2M SDE
Steps
40
Guidance
5
Seed
164787713
Laki
1248x1824
Prompt
masterpiece, best quality, highres, photorealistic picture, adult woman, dressed in a red sequin cocktail dress, one-shoulder design, (white fur palantine, fur cape, off shoulder), mini bag with gold accents. Shimmering red sequins, soft velvet texture, embossed leather bag, polished metal details. solo, female focus, looking at the viewer, petite, delicate features, sensual glare, medium breasts, perfect breasts, toned legs, narrow waist. Gentle head tilt, parted lips, seductive, green eyes, heavy makeup, black eyeshadow, mascara, dark lipstick, lush brown hair, (rose tattoo, shoulder tattoo, intricate details). sitting in a black velvet chair in a professional photo studio, sideway. dramatic lighting, subtle shadows, perfect hands
Negative prompt
neg_realism512, worst quality, low quality, blurry, anatomical nonsense, text, watermark, signature, loli, child
Mga setting
Sampler
Euler a
Steps
40
Guidance
5
Seed
3898792110
Laki
1248x1824
Prompt
masterpiece, best quality, highres, realistic, 1girl, 20 year old, (medium breasts:1.2), upper body, portrait, perfect face, detailed eyes, (bold rockabilly) young woman, curvy build, extra long red double buns hair, indian, mocha skin, brown eyes, wearing a checkered crop top, cuffed jeans, retro sneakers, red lipstick, bangle bracelets, set in a 1950s diner, with checkered floors, red vinyl booths, neon lights, vintage jukebox, and classic bar stools, during sunset
Negative prompt
worst quality, low quality, blurry, anatomical nonsense, text, watermark, signature, loli, child
Mga setting
Sampler
DPM++ 2M SDE
Steps
40
Guidance
5
Seed
164787704
Laki
1248x1824
Prompt
masterpiece, best quality, highres, Photorealistic, ultra detailed, detailed eyes, (fantasy setting):1.3, dutch angle, 1girl, solo, hands behind head, (cropped white shirt:1.4), navel, stomach, looking at viewer, seductive smile, lidded eyes, elf, long pointed ears, (orange hair with black highlights:1.4), medium hair, pale skin, freckles, beautiful, athletic, flat chest, petite, blue eyes, black leather slave collar with silver studs, standing, back against wall, dark alley, black leather shorts, black and white striped stockings
Negative prompt
neg_realism512, worst quality, low quality, blurry, anatomical nonsense, text, watermark, signature, loli, child
Mga setting
Sampler
Euler a
Steps
40
Guidance
5
Seed
3898792114
Laki
1248x1824
Prompt
masterpiece, best quality, highres, realistic, 1girl, solo, perfect body, mature female, cyberpunk, red bodysuit, holding weapon, gloves, handgun, skin tight, elbow gloves, pilot suit, looking to the side, holding gun, from side, brown background, white hair, science fiction, red gloves, gun, two-tone bodysuit, ass, yellow eyes, bodysuit, long hair, weapon, large breasts, standing, closed mouth, breasts, holding, underground ruins
Negative prompt
worst quality, low quality, blurry, anatomical nonsense, text, watermark, signature, loli, child
Mga setting
Sampler
Euler a
Steps
40
Guidance
5
Seed
100666008
Laki
1248x1824
Prompt
masterpiece, best quality, highres, realistic, 1girl, long hair, looking at viewer, blue eyes, blonde hair, long sleeves, upper body, flower, parted lips, looking back, from behind, armor, uniform, lips, petals, rose, wavy hair, shoulder armor, pink flower, pink rose
Negative prompt
worst quality, low quality, blurry, anatomical nonsense, text, watermark, signature, loli, child
Mga setting
Sampler
Euler a
Steps
40
Guidance
5
Seed
1
Laki
1792x2304
Clip skip
2
Prompt
https://civitai.red/articles/8642 __ 1st image: masterpiece, best quality, 1girl, 1boy, princess zelda, the legend of zelda: breath of the wild, standing, kiss, hug, closed eyes, outdoors , realistic __ 2nd image: masterpiece, best quality, 1girl, face, portrait, looking at viewer, closed mouth , realistic __ 3rd image: masterpiece, best quality, 1girl, solo, blonde hair, wavy hair, angel, angel wings, halo, smile, sitting, forest, white dress , realistic __ 4th Image: masterpiece, best quality, 1girl, solo, long hair, black hair, blunt bangs, straight hair, round eyewear, cat girl, cat ears, cat tail, standing, holding cat, cat, looking at viewer, library, dark, dim lighting , realistic
Negative prompt
worst quality, bad quality
Mga setting
Sampler
Euler a
Steps
31
Guidance
4
Seed
552918351
Laki
832x1216
Clip skip
2
Ginamit na weight
1
Prompt
masterpiece, best quality, highres, realistic, 1girl, (petite, skinny:1.3), narrow waist, pink hair, detailed eyes, bangs, short hair, hair ornament, star hair ornament, star (symbol), midriff, shirt, gloves, necktie, skirt, white gloves, garrison cap, capelet, hat, leaning forward, dynamic pose, looking at viewer, smirk, cowboy shot, outdoors, back alley, dappled sunlight.
Negative prompt
worst quality, low quality, bad eyes, bad lips
Mga setting
Sampler
dpmpp_2m_sde_heun
Steps
40
Guidance
6
Seed
113507689572584
Laki
1536x2688
Prompt
masterpiece, best quality, highres, realistic, 1girl, solo, perfect body, mature female, pink hair, long hair, ass, blue eyes, round butt, wide hips, large breasts, breasts, standing, closed mouth, red bodysuit, holding weapon, gloves, red gloves, gun, two-tone bodysuit, bodysuit, handgun, skin tight, elbow gloves, pilot suit, looking to the side, holding gun, from side, cyberpunk, brown background, science fiction, underground ruins.
Negative prompt
score_6, score_5, score_4, (worst quality:1.2), (low quality:1.2), (normal quality:1.2), lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, extra limb, missing limbs, tan lines,
Mga AI model para sa paggawa ng larawan, video at teksto
Ang unnamed ixl4 xl ay isang base model para sa pamilyang Stable Diffusion XL 1.0 na nakalista sa ModelTrends.ai, isang read-only na catalog ng mga open source AI model para sa larawan, video at teksto. Ikumpara ito sa ibang Stable Diffusion XL 1.0 model, tingnan ang heat score nito para makita kung gaano ito kasikat, at buksan ito sa PirateDiffusion o BitVector para subukan.
Mag-browse ayon sa pamilya ng model
I-browse ang lahat ng model