by Lykon
Open source · 5k downloads · 62 likes
DreamShaper 7 is an AI-powered image generation model specifically optimized for creating diverse visuals from text descriptions. It excels at producing realistic images, stylized art, or illustrations while offering enhanced flexibility thanks to its improved support for LoRA (adaptation models). This model stands out for its ability to generate high-resolution images, particularly at 1024 pixels, and for striking a balance between realism and artistic styles, though it is not specialized in a single domain. It suits both digital artists and content creators looking to explore various aesthetics, from photographic landscapes to fantastical worlds. Its continuous evolution, with earlier versions focused on targeted improvements, makes it a versatile tool for a wide range of creative applications.
lykon/dreamshaper-7 is a Stable Diffusion model that has been fine-tuned on runwayml/stable-diffusion-v1-5.
Please consider supporting me:
For more general information on how to run text-to-image models with 🧨 Diffusers, see the docs.
pip install diffusers transformers accelerate
from diffusers import AutoPipelineForText2Image, DEISMultistepScheduler
import torch
pipe = AutoPipelineForText2Image.from_pretrained('lykon/dreamshaper-7', torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DEISMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")
prompt = "portrait photo of muscular bearded guy in a worn mech suit, light bokeh, intricate, steel metal, elegant, sharp focus, soft lighting, vibrant colors"
generator = torch.manual_seed(33)
image = pipe(prompt, generator=generator, num_inference_steps=25).images[0]
image.save("./image.png")
