Instructions to use LoliRimuru/moeFussion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LoliRimuru/moeFussion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("LoliRimuru/moeFussion", 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
LoRA Extraction?
#19
by Mooshie - opened
This comment has been hidden
I actually plan to do LoRA (well IA3) releases after there will be resolved one issue regarding merging IA3. Uploaded for you one experiment, it's IA3 so you need LyCORIS for it to run, it will perform best on AOM3A3 and might be usable even some other models but the comaptibility compared to standard LoRA will be really low. It will not owerride any model capabilities but it's as the name suggest experimental so expect some issues. I will be happy if you could give me some feedback regarding this experiment.
https://huggingface.co/JosefJilek/loliDiffusion/blob/main/experiments/loliDiffusionV1.1.0-EXPERIMENTAL_AOM3A3_LMB-STELLE_IA3-005.safetensors
Mooshie changed discussion status to closed