Instructions to use playgroundai/playground-v2.5-1024px-aesthetic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use playgroundai/playground-v2.5-1024px-aesthetic with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("playgroundai/playground-v2.5-1024px-aesthetic", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
How can I set parameters to generate multiple different images in the same prompt?
#13
by obtion - opened
How can I set parameters to generate multiple different images in the same prompt?
Thanks a lot
Something like this. The num_images_per_prompt variable is useful for this.
steps = 75
scale = 7
num_images_per_prompt = 3
seed = torch.randint(0, 1000000, (1,)).item()
generator = torch.Generator(device=device).manual_seed(seed)
output = pipe(prompt, negative_prompt=negative_prompt, width=1024, height=1280, num_inference_steps=steps,
guidance_scale=scale, num_images_per_prompt=num_images_per_prompt, generator=generator)
obtion changed discussion status to closed