Spustit lokálně
pixelAlchemy_v30.safetensors
6.46 GB · SafeTensor · fp16 · full
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
O tomto modelu
STABLE DIFFUSION XL 1.0 · Základní modely
by Adel AI - a general stylish model for realism or digital paintings. Leans towards realism. Pixel Alchemy 30 Recommended settings : · Sampler: dpm2m · CFG: 4-7 · Steps: 30 - 40
Poznámky autora
Pixel Alchemy 30
Recommended settings :
· Sampler: dpmpp_2m_sde_gpu
· Scheduler : sgm_uniform
· CFG: 4
· Steps: 30 - 40
Pixel Alchemy Hyper V20 & V22
Improvement of human body and hands from the merger of the unreleased Pixel Alchemy V2.0 and Hyper-SDXL-12 steps CFG LoRA
Settings (ComfyUI) : Sampler : heunpp2, ddim, Euler/ Scheduler : sgm_uniform, ddim_uniform, simple / Steps : 16 to 20 / cfg : 2.5 to 3
For A1111, I won't be able to give any recommendations, because I don't use it, but I think that with a few tests you will end up finding what works best.
Pixel Alchemy Hyper V16
It's a merging of Pixel Alchemy V1.6 model with 2 LoRAs :
-
Hyper-SDXL-12 steps CFG LoRA :
-
Hand Detail XL LoRA :
Settings (ComfyUI):
Sampler : ddim / Scheduler : ddim_uniform / Steps : 20 / cfg : 3
Sampler : Euler / Scheduler : Simple / Steps : 14 / cfg : 2.5
Sampler : heunpp2/ Scheduler : sgm_uniform / Steps : 18 / cfg : 2.5
but feel free to test others settings, specially for A1111
Pixel Alchemy V16
Version 1.6 of Pixel Alchemy brings a significant improvement in the rendering of photorealistic portraits, the texture of the skin appears more natural.
It's a merging of Pixel Alchemy V1.3 with 1 checkpoint and 2 LoRAs
-
RealVisXl model :
-
Steve McCurry - Photography SDXL LoRa :
-
Essenz - Better Photography (Style LoRa for SDXL 1.0) :
Pixel Alchemy V13
It's a merge of 4 checkpoints and 3 LORAs (see list below).
One of the main goals is was to obtain a very versatile checkpoint. It's NSFW one.
Quite efficient in rendering landscapes, realistic portraits, surrealism and gives better results with noise reinjection in ComfyUI (see below, the recommended extension)
All my uploaded images were generated with low strength ADetailer (Eyes / hands / Face).
Models merged in:
-
Omnium :
-
Realism Engine SDXL :
-
Crystal Clear XL :
-
Juggernaut :
LoRAs merged in:
-
Detail Tweaker XL :
-
xl more art-full / xl_real / Enhancer :
-
SDXL Film Photography Style :
Recommended settings :
· Sampler: dpmpp_2m / Euler / heunpp2 / dpmpp_3m_sde_gpu
· Scheduler : Karras / Exponentiel / sgm_uniform
· CFG: 5 - 7
· Steps: 36 - 46
SHA256
5590EF4D4F7F117DCCE0E23B52C697C3E6396B2FA8B29280515A25D2C742016E
ID modelu ModelTrends.ai
#14897
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
DPM++ 2M Karras
Kroky
38
Guidance
7.5
Seed
438640656
Velikost
1216x832
Clip skip
2
Prompt
lazypos, Mystic Lumina
cosmic surrealism, bioluminescent, astral fantasy, ultra-detailed, divine artwork, dreamscape, celestial beings, vibrant colors, 8k
a masterpiece artwork created by celestial beings from distant galaxies, ultra-detailed and transcendent, depicting otherworldly magic and cosmic miracles unfolding in a dreamlike dimension. Bioluminescent spirit forms drift through nebula-like mist, their whispers and echoes painting the void with ethereal light. Surreal constellations pulse in harmony with shimmering auroras, as translucent beings of stardust channel ancient energies into luminous arcs of divine geometry. The scene radiates interstellar wonder, an astral daydream woven from mystic glow, sacred harmony, and galactic reverence. Celestial architecture floats in the distance, partially obscured by radiant fog, as galaxies spiral across an infinite horizon.
Negativní prompt
lazyneg
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
730927157551193
Velikost
896x1152
Prompt
photography in the style of detailed hyperrealism, dark fantasy creature, Yoji Shinkawa, James Christensen, Wayne Barlowe, Ian McQue, Roger Dean , hyper detailed, poster, artstation
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
365786185303342
Velikost
832x1216
Prompt
Art by Doug Chinnery.
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
804116262439269
Velikost
832x1216
Prompt
A photo of Eldritch Nautilus with californium and ambre floating underwater at night, wireframe, transparency, glass, intricate light, intricate artwork masterpiece, golden ratio, trending on artstation, highly detailed.
Art by John Chamberlain.
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
242500480020037
Velikost
832x1216
Prompt
An old olive tree Art by Doug Chinnery.
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
60419198077320
Velikost
896x1152
Prompt
abstract artistic representation of Prometheus, art by Paul Lovering, Antonio J. Manzanedo.
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
622351080685115
Velikost
896x1152
Prompt
Minimalism, a portrait of a beautiful woman, abstract, simple geometic shapes, hard edges, sleek contours, art by Tomer Hanuka.
Nastavení
Sampler
dpmpp_2m_sde_gpu
Kroky
30
Guidance
4
Seed
707665507176491
Velikost
832x1216
Prompt
a beautiful pinup portrait, art by Ben Templesmith & Russ Mills
Podobné modely
AI modely pro generování obrázků, videa a textu
pixelalchemy3 xl je základní model pro rodinu Stable Diffusion XL 1.0 uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Stable Diffusion XL 1.0, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Další modely Stable Diffusion XL 1.0Další Základní modely Stable Diffusion XL 1.0paintingsrealisticartstylesbasefantasylandscapehumanphotorealistic
Procházet podle rodiny modelů
Modely Text / LLM
411
Modely Anima
509
Modely Chroma
14
Modely Flux
1,071
Modely Flux 2 / Klein
1,237
Modely MiniMax H3
331
Modely Hunyuan
197
Modely Ideogram
20
Modely Krea2
674
Modely Qwen
17
Modely Qwen2
36
Modely Ltx2
150
Modely Stable Diffusion 1.5
6,465
Modely Stable Diffusion XL 1.0
15,432
Modely Zimage
804
Modely Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Vyrobeno v Japonsku
|
© 2026
