Instructions to use tm-hf-repo/cmghi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tm-hf-repo/cmghi with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("undefined", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("tm-hf-repo/cmghi") prompt = "cmghi" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
cmghi
Model description
Seedream based lora that is a mix between ghibli and scribble crayon for the outfit and hair:
Training prompt: convert this to a corporate memphis style thick oil pastel work of art, like an old risograph, tiny hints of ghibli
Trigger words
You should use cmghi to trigger the image generation.
INPUT
DEFAULT PROMPT
ADDING "maintain the same skin tone"
- Downloads last month
- 1


