Quantization made by Richard Erkhov.

distilgpt2-stable-diffusion - GGUF

Model creator: https://huggingface.co/FredZhang7/
Original model: https://huggingface.co/FredZhang7/distilgpt2-stable-diffusion/

Name	Quant method	Size
distilgpt2-stable-diffusion.Q2_K.gguf	Q2_K	0.06GB
distilgpt2-stable-diffusion.IQ3_XS.gguf	IQ3_XS	0.07GB
distilgpt2-stable-diffusion.IQ3_S.gguf	IQ3_S	0.07GB
distilgpt2-stable-diffusion.Q3_K_S.gguf	Q3_K_S	0.07GB
distilgpt2-stable-diffusion.IQ3_M.gguf	IQ3_M	0.07GB
distilgpt2-stable-diffusion.Q3_K.gguf	Q3_K	0.07GB
distilgpt2-stable-diffusion.Q3_K_M.gguf	Q3_K_M	0.07GB
distilgpt2-stable-diffusion.Q3_K_L.gguf	Q3_K_L	0.07GB
distilgpt2-stable-diffusion.IQ4_XS.gguf	IQ4_XS	0.07GB
distilgpt2-stable-diffusion.Q4_0.gguf	Q4_0	0.08GB
distilgpt2-stable-diffusion.IQ4_NL.gguf	IQ4_NL	0.08GB
distilgpt2-stable-diffusion.Q4_K_S.gguf	Q4_K_S	0.08GB
distilgpt2-stable-diffusion.Q4_K.gguf	Q4_K	0.08GB
distilgpt2-stable-diffusion.Q4_K_M.gguf	Q4_K_M	0.08GB
distilgpt2-stable-diffusion.Q4_1.gguf	Q4_1	0.08GB
distilgpt2-stable-diffusion.Q5_0.gguf	Q5_0	0.09GB
distilgpt2-stable-diffusion.Q5_K_S.gguf	Q5_K_S	0.09GB
distilgpt2-stable-diffusion.Q5_K.gguf	Q5_K	0.09GB
distilgpt2-stable-diffusion.Q5_K_M.gguf	Q5_K_M	0.09GB
distilgpt2-stable-diffusion.Q5_1.gguf	Q5_1	0.09GB
distilgpt2-stable-diffusion.Q6_K.gguf	Q6_K	0.1GB
distilgpt2-stable-diffusion.Q8_0.gguf	Q8_0	0.12GB

Original model description:

license: creativeml-openrail-m tags: - stable-diffusion - prompt-generator - distilgpt2 datasets: - FredZhang7/krea-ai-prompts - Gustavosta/Stable-Diffusion-Prompts - bartman081523/stable-diffusion-discord-prompts widget: - text: "amazing" - text: "a photo of" - text: "a sci-fi" - text: "a portrait of" - text: "a person standing" - text: "a boy watching"

DistilGPT2 Stable Diffusion Model Card

Version 2 is here!

DistilGPT2 Stable Diffusion is a text generation model used to generate creative and coherent prompts for text-to-image models, given any text. This model was finetuned on 2.03 million descriptive stable diffusion prompts from Stable Diffusion discord, Lexica.art, and (my hand-picked) Krea.ai. I filtered the hand-picked prompts based on the output results from Stable Diffusion v1.4.

Compared to other prompt generation models using GPT2, this one runs with 50% faster forwardpropagation and 40% less disk space & RAM.

PyTorch

pip install --upgrade transformers

from transformers import GPT2Tokenizer, GPT2LMHeadModel

# load the pretrained tokenizer
tokenizer = GPT2Tokenizer.from_pretrained('distilgpt2')
tokenizer.add_special_tokens({'pad_token': '[PAD]'})
tokenizer.max_len = 512

# load the fine-tuned model
model = GPT2LMHeadModel.from_pretrained('FredZhang7/distilgpt2-stable-diffusion')

# generate text using fine-tuned model
from transformers import pipeline
nlp = pipeline('text-generation', model=model, tokenizer=tokenizer)
ins = "a beautiful city"

# generate 10 samples
outs = nlp(ins, max_length=80, num_return_sequences=10)

# print the 10 samples
for i in range(len(outs)):
    outs[i] = str(outs[i]['generated_text']).replace('  ', '')
print('\033[96m' + ins + '\033[0m')
print('\033[93m' + '\n\n'.join(outs) + '\033[0m')

Example Output: