pixart-900m-1024-ft-v0.7-stage1

This is a full rank finetune derived from ptx0/pixart-900m-1024-ft-v0.7-stage1.

The main validation prompt used during training was:

a cute anime character named toast, holding a sign that reads SOON

Validation settings

CFG: 4.0
CFG Rescale: 0.7
Steps: 30
Sampler: None
Seed: 420420420
Resolution: 1024x1024

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

Prompt
unconditional (blank prompt)

Negative Prompt
blurry, cropped, ugly

Prompt
Alien planet, strange rock formations, glowing plants, bizarre creatures, surreal atmosphere

Negative Prompt
blurry, cropped, ugly

Prompt
Alien marketplace, bizarre creatures, exotic goods, vibrant colors, otherworldly atmosphere

Negative Prompt
blurry, cropped, ugly

Prompt
Child holding a balloon, happy expression, colorful balloons, sunny day, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
a 4-panel comic strip showing an orange cat saying the words 'HELP' and 'LASAGNA'

Negative Prompt
blurry, cropped, ugly

Prompt
a hand is holding a comic book with a cover that reads 'The Adventures of Superhero'

Negative Prompt
blurry, cropped, ugly

Prompt
Underground cave filled with crystals, glowing lights, reflective surfaces, fantasy environment, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Bustling cyberpunk bazaar, vendors, neon signs, advanced tech, crowded, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Cyberpunk hacker in a dark room, neon glow, multiple screens, intense focus, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
a cybernetic anne of green gables with neural implant and bio mech augmentations

Negative Prompt
blurry, cropped, ugly

Prompt
Post-apocalyptic cityscape, ruined buildings, overgrown vegetation, dark and gritty, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Magical castle in a lush forest, glowing windows, fantasy architecture, high resolution, detailed textures

Negative Prompt
blurry, cropped, ugly

Prompt
Ruins of an ancient temple in an enchanted forest, glowing runes, mystical creatures, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Mystical forest, glowing plants, fairies, magical creatures, fantasy art, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Magical garden with glowing flowers, fairies, serene atmosphere, detailed plants, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
Whimsical garden filled with fairies, magical plants, sparkling lights, serene atmosphere, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Majestic dragon soaring through the sky, detailed scales, dynamic pose, fantasy art, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
Fantasy world, floating islands in the sky, waterfalls, lush vegetation, detailed landscape, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus

Negative Prompt
blurry, cropped, ugly

Prompt
Space battle scene, starships fighting, laser beams, explosions, cosmic background

Negative Prompt
blurry, cropped, ugly

Prompt
Abandoned fairground at night, eerie rides, ghostly figures, fog, dark atmosphere, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Spooky haunted mansion on a hill, dark and eerie, glowing windows, ghostly atmosphere, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
a hardcover physics textbook that is called PHYSICS FOR DUMMIES

Negative Prompt
blurry, cropped, ugly

Prompt
Epic medieval battle, knights in armor, dynamic action, detailed landscape, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
Bustling medieval market with merchants, knights, and jesters, vibrant colors, detailed

Negative Prompt
blurry, cropped, ugly

Prompt
Cozy medieval tavern, warm firelight, adventurers drinking, detailed interior, rustic atmosphere

Negative Prompt
blurry, cropped, ugly

Prompt
Forest with neon-lit trees, glowing plants, bioluminescence, surreal atmosphere, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Bright neon sign in a busy city street, 'Open 24 Hours', bold typography, glowing lights

Negative Prompt
blurry, cropped, ugly

Prompt
Vibrant neon sign, 'Bar', bold typography, dark background, glowing lights, detailed design

Negative Prompt
blurry, cropped, ugly

Prompt
Pirate ship on the high seas, stormy weather, detailed sails, dramatic waves, photorealistic

Negative Prompt
blurry, cropped, ugly

Prompt
Pirate discovering a treasure chest, detailed gold coins, tropical island, dramatic lighting

Negative Prompt
blurry, cropped, ugly

Prompt
a photograph of a woman experiencing a psychedelic trip. trippy, 8k, uhd, fractal

Negative Prompt
blurry, cropped, ugly

Prompt
Cozy cafe on a rainy day, people sipping coffee, warm lights, reflections on wet pavement, photorealistic

Negative Prompt
blurry, cropped, ugly

Prompt
1980s arcade, neon lights, vintage game machines, kids playing, vibrant colors, nostalgic atmosphere

Negative Prompt
blurry, cropped, ugly

Prompt
1980s game room with vintage arcade machines, neon lights, vibrant colors, nostalgic feel

Negative Prompt
blurry, cropped, ugly

Prompt
Robot blacksmith forging metal, sparks flying, detailed workshop, futuristic and medieval blend

Negative Prompt
blurry, cropped, ugly

Prompt
Sleek robot performing a dance, futuristic theater, holographic effects, detailed, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
High-tech factory where robots are assembled, detailed machinery, futuristic setting, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Garden tended by robots, mechanical plants, colorful flowers, futuristic setting, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Cute robotic pet, futuristic home, sleek design, detailed features, friendly and animated

Negative Prompt
blurry, cropped, ugly

Prompt
cctv trail camera night time security picture of a wendigo in the woods

Negative Prompt
blurry, cropped, ugly

Prompt
Astronaut exploring an alien planet, detailed landscape, futuristic suit, cosmic background

Negative Prompt
blurry, cropped, ugly

Prompt
Futuristic space station orbiting a distant exoplanet, sleek design, detailed structures, cosmic backdrop

Negative Prompt
blurry, cropped, ugly

Prompt
a person holding a sign that reads 'SOON'

Negative Prompt
blurry, cropped, ugly

Prompt
Steampunk airship in the sky, intricate design, Victorian aesthetics, dynamic scene, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Steampunk inventor in a workshop, intricate gadgets, Victorian attire, mechanical arm, goggles

Negative Prompt
blurry, cropped, ugly

Prompt
Stormy ocean with towering waves, dramatic skies, detailed water, intense atmosphere, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
Dramatic stormy sea, lighthouse in the distance, lightning striking, dark clouds, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Graffiti artist creating a mural, vibrant colors, urban setting, dynamic action, high resolution

Negative Prompt
blurry, cropped, ugly

Prompt
Urban alleyway filled with vibrant graffiti art, tags and murals, realistic textures

Negative Prompt
blurry, cropped, ugly

Prompt
Urban street sign, 'Main Street', bold typography, realistic textures, weathered look

Negative Prompt
blurry, cropped, ugly

Prompt
Classic car show with vintage vehicles, vibrant colors, nostalgic atmosphere, high detail

Negative Prompt
blurry, cropped, ugly

Prompt
Retro diner sign, 'Joe's Diner', classic 1950s design, neon lights, weathered look

Negative Prompt
blurry, cropped, ugly

Prompt
Vintage store sign with elaborate typography, 'Antique Shop', hand-painted, weathered look

Negative Prompt
blurry, cropped, ugly

Prompt
A cinematic portrait photograph of a white tiger in a lush forest at twilight

Negative Prompt
blurry, cropped, ugly

Prompt
A landscape photograph of a small cottage in the middle of a field of wild flowers with mountains off in the distance at sunset

Negative Prompt
blurry, cropped, ugly

Prompt
A portrait photograph of a young black woman wearing a ball gown in a mansion

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph of a sleek and modern house interior with plants and foliage all over the place

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph of a snowy forest and river from above at dusk

Negative Prompt
blurry, cropped, ugly

Prompt
A macro photograph of a lady bug on the petal of a rose

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph of a traditional Japanese meal on top of a bamboo desk

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph of a small fairy house covered in mushrooms moss and flowers in a sunny forest

Negative Prompt
blurry, cropped, ugly

Prompt
A cinematic landscape photograph of an organic geometric building at night time

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph of an abstract cake inspired off of marble and art deco

Negative Prompt
blurry, cropped, ugly

Prompt
painting of a water color fart that was both silent and deadly

Negative Prompt
blurry, cropped, ugly

Prompt
cleavage shot of harley quinn, fujifilm XT3 sharp focus kodak moment

Negative Prompt
blurry, cropped, ugly

Prompt
a woman doing yoga, fujifilm XT3 sharp focus kodak moment

Negative Prompt
blurry, cropped, ugly

Prompt
a black and white photo of a woman, dress shirt, somewhat androgenic, one model, rugged, sydney, taken with a canon eos 5d, rugged and dirty, focus on girl, boyish, brigitte, photographed, blue steel, youth, charlie immer, without makeup, uniquely beautiful, on the street, lady kima

Negative Prompt
blurry, cropped, ugly

Prompt
obama with his shirt off, muscles flexing

Negative Prompt
blurry, cropped, ugly

Prompt
muscle-bound obama, shirtless, flexing, fujifilm XT3 sharp focus kodak moment

Negative Prompt
blurry, cropped, ugly

Prompt
donald trump as a religious icon, protestant church-goer, fujifilm XT3 sharp focus kodak moment

Negative Prompt
blurry, cropped, ugly

Prompt
a stunning portrait of a shirtless, muscle-bound Justin Trudeau, Canadian Prime Minister bodybuilder, fujifilm XT3 sharp focus kodak moment

Negative Prompt
blurry, cropped, ugly

Prompt
a stunning portrait of a shirtless, muscle-bound John Madden bodybuilder, fujifilm XT3 sharp focus kodak moment

Negative Prompt
blurry, cropped, ugly

Prompt
a portrait of edward scissorhands looking down at his cellphone, fujifilm XT3

Negative Prompt
blurry, cropped, ugly

Prompt
john cena, clown baby, fujifilm XT3, sharp focus

Negative Prompt
blurry, cropped, ugly

Prompt
stunning and impossible caustics experiment, suspended liquids, amorphous liquid forms, high intensity light rays, unreal engine 5, raytracing, 4k, laser dot fields, curving light energy beams, glowing energetic caustic liquids, thousands of prismatic bubbles, quantum entangled light rays from other dimensions, negative width height, recursive dimensional portals

Negative Prompt
blurry, cropped, ugly

Prompt
terrified pixar child in their bedroom looking up at the ceiling as a glowing red uranium core melts through the ceiling

Negative Prompt
blurry, cropped, ugly

Prompt
stunning portrait of john cusack as a twisted jester at the mardi gras carnival, epic, cinematic, 8k

Negative Prompt
blurry, cropped, ugly

Prompt
stunning portrait of a beer bottle (with a label that says "LIGMA GRAVY")1.4 full of gravy, epic, cinematic, advertisement

Negative Prompt
blurry, cropped, ugly

Prompt
stunning++ photographs of luchador+ wrestlers at the twisted carnival-

Negative Prompt
blurry, cropped, ugly

Prompt
The unforeseen friendship: a crow and a cat share a quiet moment, upending the laws of the natural world

Negative Prompt
blurry, cropped, ugly

Prompt
A breathtaking landscape of a mystical anime village surrounded by cherry blossoms at sunrise

Negative Prompt
blurry, cropped, ugly

Prompt
A dramatic portrait of an anime hero poised for battle against a dystopian cityscape backdrop

Negative Prompt
blurry, cropped, ugly

Prompt
A towering, battle-ready mecha robot standing amidst ruins, fujifilm XT3 sharp focus

Negative Prompt
blurry, cropped, ugly

Prompt
A sumptuous anime-style feast laid out on a traditional Japanese tatami mat

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph capturing an epic fantasy anime scene with dragons flying over ancient castles at twilight

Negative Prompt
blurry, cropped, ugly

Prompt
A neon-lit nighttime bustling anime cityscape, with vivid colors and futuristic architecture

Negative Prompt
blurry, cropped, ugly

Prompt
two anime characters in a high-energy duel, swords clashing with sparks flying

Negative Prompt
blurry, cropped, ugly

Prompt
A cute anime character with their adorable, mystical pet creature in a magical forest

Negative Prompt
blurry, cropped, ugly

Prompt
A lively anime school scene, students in uniform bustling around in a cherry-blossom-filled courtyard

Negative Prompt
blurry, cropped, ugly

Prompt
A enchanting underwater anime world, with mermaids and exotic sea creatures amidst coral reefs

Negative Prompt
blurry, cropped, ugly

Prompt
A breathtaking space anime scene, with starships battling among the stars and nebulas

Negative Prompt
blurry, cropped, ugly

Prompt
A photograph showcasing a cyberpunk anime street scene, neon lights reflecting off rain-slicked streets

Negative Prompt
blurry, cropped, ugly

Prompt
A serene anime spirit wandering through an ethereal, mist-covered forest

Negative Prompt
blurry, cropped, ugly

Prompt
A powerful lone anime samurai standing tall against a backdrop of a setting sun and ancient temples

Negative Prompt
blurry, cropped, ugly

Prompt
A anime cooking showdown, chefs in a frantic battle with flames and flying ingredients

Negative Prompt
blurry, cropped, ugly

Prompt
A serene anime winter landscape, a small village blanketed in snow with characters in colorful kimonos

Negative Prompt
blurry, cropped, ugly

Prompt
A vibrant anime-style festival, lanterns glowing and characters in traditional attire dancing joyfully

Negative Prompt
blurry, cropped, ugly

Prompt
a cute anime character named toast, holding a sign that reads SOON

Negative Prompt
blurry, cropped, ugly

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

Training epochs: 6
Training steps: 220000
Learning rate: 1e-06
Effective batch size: 64
- Micro-batch size: 8
- Gradient accumulation steps: 1
- Number of GPUs: 8
Prediction type: epsilon
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Xformers: Enabled

Datasets

sports

Repeats: 0
Total number of images: ~768
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

mj-60

Repeats: 0
Total number of images: ~179136
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

id-75k

Repeats: 0
Total number of images: ~36224
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

celebrities

Repeats: 0
Total number of images: ~1088
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

normalnudes

Repeats: 0
Total number of images: ~1024
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

guys

Repeats: 0
Total number of images: ~320
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

signs

Repeats: 0
Total number of images: ~320
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

dalle3

Repeats: 0
Total number of images: ~1112704
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

sfwbooru

Repeats: 0
Total number of images: ~395136
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

moviecollection

Repeats: 0
Total number of images: ~1792
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

bookcovers

Repeats: 0
Total number of images: ~704
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

nijijourney

Repeats: 0
Total number of images: ~512
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

experimental

Repeats: 0
Total number of images: ~3008
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

ethnic

Repeats: 0
Total number of images: ~3072
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

gay

Repeats: 0
Total number of images: ~1088
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

architecture

Repeats: 0
Total number of images: ~4352
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

shutterstock

Repeats: 0
Total number of images: ~21056
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

midjourney-v6-520k-raw

Repeats: 0
Total number of images: ~390976
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

nijijourney-v6-520k-raw

Repeats: 0
Total number of images: ~416064
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

cinemamix-1mp

Repeats: 0
Total number of images: ~7232
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

nsfw-1024

Repeats: 0
Total number of images: ~10752
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

anatomy

Repeats: 5
Total number of images: ~16384
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

bg20k-1024

Repeats: 0
Total number of images: ~89280
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

yoga

Repeats: 0
Total number of images: ~3584
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

photo-aesthetics

Repeats: 0
Total number of images: ~33088
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

text-1mp

Repeats: 5
Total number of images: ~13184
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'pixart-900m-1024-ft-v0.7-stage1'
pipeline = DiffusionPipeline.from_pretrained(model_id)

prompt = "a cute anime character named toast, holding a sign that reads SOON"
negative_prompt = "blurry, cropped, ugly"

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt='blurry, cropped, ugly',
    num_inference_steps=30,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1152,
    height=768,
    guidance_scale=4.0,
    guidance_rescale=0.7,
).images[0]
image.save("output.png", format="PNG")

terminusresearch
/

pixart-900m-1024-ft-v0.7-stage1