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
Using DDIMScheduler in Playground v2.5
#35
by XinyangATK - opened
Hi everyone,
Recently I'd like to visualize the intermediate image during each step, I need to decode "pred_x0" based on current latent. However, when I use "DDIMScheduler" to get the "pred_x0", the results always failed that the model always generated bad images. Is there any solution to this issue with DDIMScheduler or is there any other methods to achieve this function with other scheduler?