How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("NullAxis/karmix-merge-experiments", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

This repository is an offshoot from the main Karmix-XL v0 (https://huggingface.co/chemwolf/Karmix-XL-v0) model with experimental versions of the model using various methods/parameters for merging.

The models are provided "as is", and due to the experimentation, perfect work is not guaranteed.

These versions are not release versions and remain only prototypes that do not reflect the future of the model.

Additional information about the existing versions will be added later.

Downloads last month
110
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for NullAxis/karmix-merge-experiments

Finetuned
(4)
this model
Finetunes
3 models
Merges
5 models