Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
Instructions to use gsdf/Counterfeit-V2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use gsdf/Counterfeit-V2.5 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-V2.5", 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
differences in vae file?
#20
by ppbrown - opened
in the vae subdir there are safetensor and .pt files, approximately the same size.
At the top level, there is a .pt file that is TWICE THE SIZE (and probably the one that triggered the virus warning?)
The annoying thing is.. the top level one produces BETTER results, in my opinion.
Can anyone shed light on why the difference.... and ideally, how to safely convert that top level one to a safetensor, ensureing it only has actual "safe tensors" in it?