Instructions to use gsdf/Counterfeit-V2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gsdf/Counterfeit-V2.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("gsdf/Counterfeit-V2.0", 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
I can't load the model in google colab
#10
by DominosXpizza - opened
It's pretty straightforward when I try to load the model with colab I get some error...
Has this ever happened to anyone? How can I fix it ?
It block specifically at :
Loading weights [8838e0d1fb] from /content/stable-diffusion-webui/models/Stable-diffusion/Counterfeit-V2.0.ckpt
^C
Use the fp16 safetensors version. You probably ran out of RAM on colab.
Yeah that was the problem I figured out after some time
you can use the full 7 gigs model if you use .safetensors
That why it work... Thanks for the clarification