Run Locally
k2-pixel32.safetensors
71 MB · SafeTensor · bf16
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
KREA2 · LoRAs
by _Envy_ - Krea 2 Pixel Art 32x32
Creator notes
So it turns out that Krea is naturally amazing at pixel art, and it just needs a little nudge to help it get to a consistent resolution. This is a set of pixel art loras intended to be run at exactly 1024x1024.
I created a custom node for post-processing:
It just downscales the image to the specified resolution, palette-reduces it, and optionally upscales it back. Because the pixels are (almost) always a constant size, it doesn't try to do any guesswork about rows and columns. If you don't want to use this node, you can do the same thing in your favorite paint program.
Trigger words
16-bit pixel art
texture
sprite
icon
SHA256
35A79DAF8C9499554C5CD299DC3940F78C2D5F0B4EF30B3AD42EA232CDF14AF0
ModelTrends.ai Model ID
#27176
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
euler
Steps
12
Guidance
1.2
Seed
554346234
Size
1024x1024
Weight used
1
Prompt
1970s tabletop fantasy rpg manual illustration, 16-bit pixel art,
Sprite of Hork the Orc pastry chef is advertising his bakery.
Settings
Sampler
euler
Steps
9
Guidance
1
Seed
1621768526
Size
832x1248
Weight used
1
Prompt
16-bit pixel art, @NJSW33T, zidiusArt, A low-angle, worm's-eye perspective captures Hatsune Miku in a whirlwind of kinetic energy, her silhouette slicing through the haze of a 1970s discotheque. She is draped in a shimmering, high-collared disco jumpsuit of iridescent silver sequins and satin, the fabric catching the erratic pulse of neon lights. Her joyful expression is radiant, a wide, genuine smile revealing a glimpse of white teeth as she leans into a dramatic, gravity-defying dance move. In the midground, the blurred silhouettes of a captivated crowd sway in rhythmic synchronization, their forms softened by a thick, swirling fog of dry ice. Above, a massive mirrored disco ball fractures the light into a thousand dancing shards across the mahogany-paneled walls. The color palette is a clash of electric magenta, deep indigo, and shimmering gold, illuminated by harsh, colorful spotlights that create high-contrast shadows. Captured with a wide-angle 14mm lens to distort the spatial geometry, the image feels like a frenetic snapshot of euphoria. The atmosphere is thick with the scent of ozone and perfume, rendered in the saturated, grainy aesthetic of a vintage Kodachrome film still.
Negative prompt
extra arms, extra hands, extra fingers, bad anatomy, deformed hands, malformed sword, duplicate weapon, blurry, low quality, oversaturated, text, watermark, logo, signature, bokeh, child, nsfw
Settings
Sampler
euler
Steps
12
Guidance
1.2
Seed
1312722170
Size
1024x1024
Weight used
1
Prompt
1970s tabletop fantasy rpg manual illustration, 16-bit pixel art,
A dark magical flame burning mysteriously in a dark forest.
Settings
Size
1152x1152
Prompt
multiple prompts
Settings
Sampler
euler
Steps
12
Guidance
1.2
Seed
499702959
Size
1024x1024
Weight used
1
Prompt
1970s tabletop fantasy rpg manual illustration, 16-bit pixel art,
Portrait of Chaddicus, the human adventurer. Confident, almost cocky.
Settings
Sampler
euler
Steps
12
Guidance
1.2
Seed
1226264056
Size
1024x1024
Weight used
1
Prompt
1970s tabletop fantasy rpg manual illustration, 16-bit pixel art,
Portrait of a male elf bandit. Scars, missing the tip of an ear, slender but rugged appearance. Forest camp background.
AI Models for Image, Video & Text Generation
pixel art32 krea2 is a LoRA for the Krea2 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Krea2 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

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