dzungpham
/

font-architect

contrastive-learning

font-generation

character-synthesis

Model card Files Files and versions

font-architect / FST /checkpoint_step_1500

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

dzungpham's picture

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss

3011a43 verified 2 months ago

content_encoder.safetensors

4.76 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
fst_module.safetensors

239 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
fst_projection.safetensors

4.2 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
identity_loss_module.safetensors

194 kB
xet

Training FST with constant lr, switch to cosine or linear please 2 months ago
mss_encoder.safetensors

25.3 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
original_style_projection.safetensors

4.2 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
style_encoder.safetensors

82.4 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
training_state.pth
Detected Pickle imports (3)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
1.35 GB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago
unet.safetensors

315 MB
xet

FST training for 500, 1000 and 1500 steps phase 1 with consistency loss, no identity loss 2 months ago