metadata

license: creativeml-openrail-m
language:
  - en
library_name: diffusers
pipeline_tag: text-to-image
base_model: stabilityai/stable-diffusion-2
tags:
  - code
  - safetensors
  - stable-diffusion
  - scheduler
  - text_encoder
  - tokenizer
  - unet
  - vae
inference:
  parameters:
    num_inference_steps: 7
    guidance_scale: 3
    negative_prompt: >-
      (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong
      anatomy, extra limb, missing limb, floating limbs, (mutated hands and
      fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting,
      blurry, amputation

**Samim Kumar Patel, Pretrained Model, With proper use of best Hyperparameters for Business UseCases for Production Level*

Introducing the pretrained Model from the base Model called stabilityai/stable-diffusion-2, which is very fast and production deployable. It is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.

Diffusers usage

pip install torch diffusers

from diffusers import StableDiffusionPipeline
import torch

model_id = "samim2024/text-to-image"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]  
    
image.save("astronaut_rides_horse.png")