Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
stable-diffusion
image-to-image
art
magic-the-gathering
mtg
Instructions to use volrath50/fantasy-card-diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use volrath50/fantasy-card-diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("volrath50/fantasy-card-diffusion", 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 Settings
- Draw Things
- DiffusionBee
"Training and dataset" no info on base model.
#2
by Corshi - opened
I understand that dreambooth models are made on some kind of base model.
That info helps understanding the other prompts included to the model, as it also is a clue in case of merging.
I assume it is SD1.5, just because how it is able to understand characters from different media, but just making sure anyway.
It is amazing model. Install "like", and I really had no idea I needed this in my life.
I'm really happy you made this model <3
Thanks. Really happy to have other people enjoy it. :)
Base model is in fact SD-v1.5 - I'll update the readme to reflect that.
Corshi changed discussion status to closed