Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
pixelArtDiffusionXL_spriteShaper.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<spriteshaper-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
Yamer
on Civitai
PixelShaper by Yamer is a 20% merge from HuskyAI's pixel art model. This Pixel Art Diffusion is a dedicated checkpoint designed for creating pixel art style images. It has the capability to generate a wide variety of images in the pixel art style, allowing users to produce beautiful and creative artworks. While it may not focus on generating perfectly shaped pixels, it excels in delivering images with the distinctive pixel art style, offering advantages such as vibrant color saturation and the convenience of shorter prompts. You have total freedom over what this checkpoint can create, use it to generate videos or game assets or even to explore a new style. How To Use: This checkpoint can be hard to use when generating images without knowing how to get the best images with it, here is a simple list of things to follow to generate beautiful art: Keep the prompt simple, don't use extremely long prompts, focus on what you need Use "Pixel Art" at the start or in the beginning part of the prompt, this way you can be sure to achive a pixel art type of image Use words such as 16 bit, 32 and 64 bit to help the checkpoint understand the style if you are having a hard time getting pixel art When upscaling remember to use very low Denoise Strength values, don't go above 0.25 or else the image will start to distort It's preferrable if you don't use words that imply a style that is very different from pixel art, especially in the beginning part of the prompt, prompts such as: realistic, Ph
Creator notes
For business inquires, commercial licensing, consultation and large scale image captioning for datasets contact me under , for custom LoRAs visit my . Follow me on Twitter: Discord: yamer_ai If you have enjoyed this checkpoint: --> REDESTRIBUTION OF THIS MODEL TO PLATFORMS OUTSIDE CIVITAI AND SELLING IMAGES WITHOUT MY WRITTEN CONSENT IS FORBIDDEN! <--- You can contact me on Discord: (yamer_ai), Twitter: , email: or directly using the Civitai chat system for my approval. Pixel Art Diffusion is a dedicated checkpoint designed for creating pixel art style images. It has the capability to generate a wide variety of images in the pixel art style, allowing users to produce beautiful and creative artworks. While it may not focus on generating perfectly shaped pixels, it excels in delivering images with the distinctive pixel art style, offering advantages such as vibrant color saturation and the convenience of shorter prompts. You have total freedom over what this checkpoint can create, use it to generate videos or game assets or even to explore a new style. The VAE has been already baked in. How To Use: This checkpoint can be hard to use when generating images without knowing how to get the best images with it, here is a simple list of things to follow to generate beautiful art: - Keep the prompt simple, don't use extremely long prompts, focus on what you need - Use "Pixel Art" at the start or in the beginning part of the prompt, this way you can be sure to achive a pixel art type of image - Use words such as 16 bit, 32 and 64 bit to help the checkpoint understand the style if you are having a hard time getting pixel art - When upscaling remember to use very low Denoise Strength values, don't go above 0.25 or else the image will start to distort - It's preferrable if you don't use words that imply a style that is very different from pixel art, especially in the beginning part of the prompt, prompts such as: realistic, Photography and hyper detailed may damage the pixel art aesthetic, use those only in the last parts of a prompt (if you want to use them at all) - Keep in mind this is not a perfect pixel art image creator, images generated won't necessarily have pixel perfect squares, square may vary slightly in size - Use CFG values between 4 and 12 this way the model is more stable and can generate images better - Pay attention to the LoRAs you are using, some may completely remove the pixel art style from the image What Are The Best Uses? You have the freedom to create what you prefer, here are some fields where this checkpoint is best used: - Game design, generate images to use as inspiration for sprites in video games, tools, potions, armors and everything else you need for a pixelated game adventure - Profile pictures, use it to generate your very own and unique profile picture for all social media platforms - Commercial use, interested in using this for your next game/AI related projects? Contact me on my mail () - Learning tool, learn how to make pixel art by generating images with this checkpoint and trying to remake it using external drawing software - Animations, generate videos with the pixel art aesthetic, this checkpoint can handle animations, see some examples made by RAMTHURST in the gallery below - Experimentation, have fun and make something really unique with it, share with friends and enjoy what you create Creator Note: Hi, I'm an Italian creator, I love AI and share what I create with others to spread the joy of using AI. I craft checkpoints, LoRAs and prompts that anyone can use to generate their own art and share it. My ultimate aim is to be a good creator, sharing the models I create as a hobby with others and see other create ever better creations than the ones I upload. The primary objective of this checkpoint is to excel in crafting pixel art at the highest capability achievable by SDXL. Future updates aim to enhance the style, making it even more refined and stable. Delve into the realm of AI-generated art with a pixel art aesthetic, and share your thoughts in the comments below. Don't forget to provide a review and share your pixelated creations for inclusion in the gallery! Unleash your creativity in the realm of 16-bit wonders and enjoy the process! 🤯 P͓̽e͓̽r͓̽s͓̽o͓̽n͓̽a͓̽l͓̽ ͓̽R͓̽a͓̽t͓̽i͓̽n͓̽g͓̽:͓̽ - Quality: 9.5/10 - Stability (Variety): 6/10, the lower = the more variety with one prompt - Style Flexibility: 3/10 - CFG resistance: 12/30 - Style strength: 9/10 - Image Stability: 9.5/10 (how much the image looks cohesive to the human eye) Recommended Settings: Image Quality: 1024x1024 (Standard for SDXL), 768x1024 (Used in the showcase) 16:9, 4:3, 6:13 Steps: 30-50 - Hires Upscaler: 4x_foolhardy_Remacri or 4xUltraSharp - Hires upscale: The only limit is your GPU (I upscale 1,5 times the base image, 576x1024) - VAE: 𝓥𝓮𝓻𝓼𝓲𝓸𝓷 2 𝓤𝓹𝓭𝓪𝓽𝓮 𝓝𝓸𝓽𝓮: The new version uses checkpoint made by . V2 has also been trained on more images and the pixel shape quality has been improved. Overall detail of the generated image is better in V2. To achieve a specific nsfw result I recommend to use a SDXL LoRA, this checkpoint can handle nsfw prompts but it is not a nsfw focused model, keep in mind that a SD 1.5 LoRA doesn't work with a SDXL models. 1) Perfect for pixel creatures, gotta generate'em all 2) Imagination is the first ingredient of AI 3) Think outside the hypercube! -Yamer Grimlock
Trigger words
pixel art
64 bit
32 bit
16 bit
27,576 downloads · 1,839 likes on Civitai
SHA256
7ADFFA28D4003A773C2D4E5F10AE1BA63C33573967864A7F9A4A3BE9C9F04A93
ModelTrends.ai Model ID
#8975
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 a
Steps
20
Guidance
8
Seed
4
Size
1024x1024
Clip skip
2
Prompt
hiroshi_nagai, japanese lady smoking overlooking city, pixel
Negative prompt
bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
3.5
Seed
2087253762
Size
832x1216
Clip skip
2
Prompt
fantasy illustration by John Howe, Akira Toriyama, hyperdetailed, hyper quality, artstation winning award, bright highlights, deep shadows
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
3.5
Seed
2087253764
Size
832x1216
Clip skip
2
Prompt
fantasy illustration by John Howe, Akira Toriyama, hyperdetailed, hyper quality, artstation winning award, bright highlights, deep shadows
Settings
Sampler
Euler a
Steps
40
Guidance
6
Seed
2733400127
Size
576x1024
Prompt
female, red under eye, under eye makeup, white eyes, white eyes, white eyelashes, blue hair, blue hair, flowing hair, flowing hair, glowing hair, glowing hair, while sharks, whale sharks, underwater, underwater, stoic face, calm face, beautiful, pretty, white dress, white dress, flowing dress, stars, stars in hair, pretty, shaded, glowing, glowing beautiful shading, glowing, under water, floating, floating
Negative prompt
bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, deformation, corrupt image
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
376658587
Size
832x1216
Clip skip
2
Prompt
pixel art, 64, cat in a basket being flown by a red balloon, sleeping, peaceful, comic style, adventure
Negative prompt
score_5, score_4, watermark, signature, artist name, 3d, muscular, cum,
Settings
Sampler
Euler a
Steps
40
Guidance
4
Seed
1747542464
Size
1024x1024
Clip skip
2
Prompt
A fancy pixel art butter in grass with knife and toasted bred beside. The dish is white and simple
Settings
Sampler
DPM++ 2M Karras
Steps
23
Guidance
7
Seed
1351013523
Size
1024x1024
Clip skip
2
Prompt
masterpiece, best quality, absurdres, year 2023, ((landscape made of crystal)), mountains, river, valley, clouds
Negative prompt
lowres, (bad), bad anatomy, bad hands, extra digits, multiple views,fewer, extra, missing, text, error, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early,chromatic aberration, signature,artistic error, username, scan,clone
Settings
Sampler
Euler a
Steps
40
Guidance
6
Seed
2142381647
Size
576x1024
Prompt
pixel art, 32 bit, a renaissance style (statue) carved out of white marble, David statue
Negative prompt
bad quality, bad anatomy, worst quality, low quality, low resolution, extra fingers, blur, blurry, ugly, wrong proportions, watermark, image artifacts, lowres, jpeg artifacts, deformed, noisy image, deformation, corrupt image
AI Models for Image, Video & Text Generation
spriteshaper xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 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
Browse all models