Instructions to use SG161222/RealVis_Medium_1.0b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SG161222/RealVis_Medium_1.0b with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SG161222/RealVis_Medium_1.0b", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Is the transformer model changed format from 35Medium?
#1
by little-lake-studios - opened
Im getting an error when loading the transformer model with my Rust pipeline that normally loads 35Mediumcannot find tensor first_stage_model.encoder.conv_in.weight