Image-to-Image
Diffusers
Safetensors
English
font-diffusion
contrastive-learning
font-generation
character-synthesis
style-transfer
dpm-solver
Instructions to use dzungpham/font-architect with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dzungpham/font-architect with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dzungpham/font-architect", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Commit History
-
Delete FST/logs
Verified signature94355cd -
Delete FST/final
Verified signature19692c5 -
Delete FST/checkpoint_step_4
Verified signatureb1c3bd9 -
Delete FST/checkpoint_step_1000
Verified signatureb85eece -
Delete FST/checkpoint_step_2
Verified signaturef37334b -
FST training for 250, 500 steps on pretrained weights of fontdiffuser
Verified signature301f441
-
FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss
Verified signature3011a43 -
Training FST with constant lr, switch to cosine or linear please
Verified signature5aa9738
-
Testing Font Diffuser with FST, MSSE, consistency loss and identity mapping loss
Verified signaturebc1c244