Lokaal uitvoeren
pixelAlchemy_v30.safetensors
6.46 GB · SafeTensor · fp16 · full
Downloads worden geleverd door Civitai. Sommige makers vragen eerst om in te loggen op Civitai.
AD
Installeren / Uitvoeren op Graydient
Lidmaatschap vereist
<pixelalchemy3-xl>
Over dit model
STABLE DIFFUSION XL 1.0 · Basismodellen
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
Notities van de maker
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
ModelTrends.ai model-ID
#14897
Inhoud melden
Voorbeeldrenders
Prompts en instellingen gedeeld door de mensen die deze renders op Civitai maakten. Kies een render om te zien hoe hij is gemaakt.
Instellingen
Sampler
DPM++ 2M Karras
Stappen
38
Guidance
7.5
Seed
438640656
Formaat
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.
Negatieve prompt
lazyneg
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
730927157551193
Formaat
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
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
365786185303342
Formaat
832x1216
Prompt
Art by Doug Chinnery.
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
804116262439269
Formaat
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.
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
242500480020037
Formaat
832x1216
Prompt
An old olive tree Art by Doug Chinnery.
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
60419198077320
Formaat
896x1152
Prompt
abstract artistic representation of Prometheus, art by Paul Lovering, Antonio J. Manzanedo.
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
622351080685115
Formaat
896x1152
Prompt
Minimalism, a portrait of a beautiful woman, abstract, simple geometic shapes, hard edges, sleek contours, art by Tomer Hanuka.
Instellingen
Sampler
dpmpp_2m_sde_gpu
Stappen
30
Guidance
4
Seed
707665507176491
Formaat
832x1216
Prompt
a beautiful pinup portrait, art by Ben Templesmith & Russ Mills
Vergelijkbare modellen
AI-modellen voor het genereren van afbeeldingen, video en tekst
pixelalchemy3 xl is een basismodel voor de Stable Diffusion XL 1.0-familie, vermeld op ModelTrends.ai, een alleen-lezen catalogus van open source AI-modellen voor afbeeldingen, video en tekst. Vergelijk het met andere Stable Diffusion XL 1.0-modellen, bekijk de populariteitsscore om de trend te zien en open het op PirateDiffusion of BitVector om het te proberen.
Meer Stable Diffusion XL 1.0-modellenMeer Stable Diffusion XL 1.0 Basismodellenpaintingsrealisticartstylesbasefantasylandscapehumanphotorealistic
Bladeren op modelfamilie
Text / LLM-modellen
411
Anima-modellen
509
Chroma-modellen
14
Flux-modellen
1,071
Flux 2 / Klein-modellen
1,237
MiniMax H3-modellen
331
Hunyuan-modellen
197
Ideogram-modellen
20
Krea2-modellen
674
Qwen-modellen
17
Qwen2-modellen
36
Ltx2-modellen
150
Stable Diffusion 1.5-modellen
6,465
Stable Diffusion XL 1.0-modellen
15,432
Zimage-modellen
804
Wan-modellen
919

Model
Trends
.ai
© ModelTrends.ai
|
Gemaakt in Japan
|
© 2026
