metadata
license: mit
datasets:
- recoilme/SyntheticPrompts
language:
- en
tags:
- gpt2
- prompts
A GPT2 model to generate prompts for SDXL or similar models.
Trained from the GPT2 small model. Attach a Style to affect the render further.
Trained on Syntetic prompts generated with Mistral7b.
Dataset: https://huggingface.co/datasets/recoilme/SyntheticPrompts
Project by AiArtLab, discord: https://discord.gg/HtXY93VW
from transformers import pipeline, GPT2Tokenizer,GPT2LMHeadModel
checkpoint_path = "recoilme/insomnia_v1"#"base"
model = GPT2LMHeadModel.from_pretrained(checkpoint_path)
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
text_generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
texts = [
"Frog in a Harry Potter costume",
"Cat, art by ",
"a photo of woman underwater",
"thunderstorms on the alien planet, very shocking",
"Standing on the land of a new planet, the Female astronaut dances",
"The face of the cat woman, a face beautiful, young. The head is adorned with the Egyptian crown of Bastet.",
]
for text in texts:
print(f"Input: {text}:")
out = text_generator(text, max_length=150, num_return_sequences=2,temperature=1.0,)
print(f"Output 1: {out[0]['generated_text']}\n\n")
print(f"Output 2: {out[1]['generated_text']}")
print("\n")
Input: Frog in a Harry Potter costume:
Output 1: Frog in a Harry Potter costume:lighting a magical scene, vibrant colors. frogs frolicking in a magical pond, detailed textures on the frog's skin. Post-processing:izard's smile replaced with a pond edge reflection, intricate patterns on the frogs' bodies. Super excited expression towards the frogs, colorful lighting enhancing every detail.
Output 2: Frog in a Harry Potter costume, complete with red cap and yellow shirt, dashing through a magical forest. The trees are ancient and gnarled, their leaves shimmering with iridescent hues. Frog's eyes are full of determination as he runs, leaving behind a trail of golden sparks. A rainbow arches overhead, adding a touch of whimsy to the scene.