--- license: mit datasets: - recoilme/SyntheticPrompts language: - en tags: - gpt2 - prompts --- Project by https://aiartlab.org/
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 ``` 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. ```