import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("akhilsharma/raja_ravi_verma", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
To use this model, use raja_ravi_verma in the prompt text.
Got some good results from this model. Adding some sample below.
Code:
from diffusers import StableDiffusionPipeline
import torch
model_id = "akhilsharma/raja_ravi_verma"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
prompt = "raja_ravi_verma painting of a girl, standing by a tree, river in the background ,ultra realistic, concept art, intricate details, eerie, highly detailed, photorealistic, 8 k"
image = pipe(prompt2, num_inference_steps=100, guidance_scale=7.5).images[0]
image.save("painting.png")
Sample images
language:
- python thumbnail: "https://i.ibb.co/pJrsRXj/makephotogallery-net-1669012445576.png" tags:
- Text-to-Image
- Indian
- Downloads last month
- -