Downloads · 30 days
11
4% of all-time downloads
dreambooth_diffusion_model_v1
kadirnar/dreambooth_diffusion_model_v1
dreambooth_diffusion_model_v1 is a text-to-image model from kadirnar. Use it when you need an image from a text prompt. It is set up for keras. The card lists the license as creativeml-openrail-m.
This the Stable Diffusion model fine-tuned the Low Poly World concept taught to Stable Diffusion with Dreambooth. It can be used by modifying the instanceprompt: a photo of lowpolyworld
All-time downloads
286
Public
Repo size
3.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data-00000-of-000013.4 GB · 99%
At a glance
- Task
- Text-to-Image
- Library
- keras
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Mar 8, 2023
- Updated
- Mar 9, 2023
- SHA
- fe1f58ca
Model card
From the Hugging Face model README
Model description
This the Stable Diffusion model fine-tuned the Low Poly World concept taught to Stable Diffusion with Dreambooth. It can be used by modifying the instance_prompt: a photo of lowpoly_world
Gradio
Demo: Gradio
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
|---|---|
| inner_optimizer.class_name | Custom>RMSprop |
| inner_optimizer.config.name | RMSprop |
| inner_optimizer.config.weight_decay | None |
| inner_optimizer.config.clipnorm | None |
| inner_optimizer.config.global_clipnorm | None |
| inner_optimizer.config.clipvalue | None |
| inner_optimizer.config.use_ema | False |
| inner_optimizer.config.ema_momentum | 0.99 |
| inner_optimizer.config.ema_overwrite_frequency | 100 |
| inner_optimizer.config.jit_compile | False |
| inner_optimizer.config.is_legacy_optimizer | False |
| inner_optimizer.config.learning_rate | 0.0010000000474974513 |
| inner_optimizer.config.rho | 0.9 |
| inner_optimizer.config.momentum | 0.0 |
| inner_optimizer.config.epsilon | 1e-07 |
| inner_optimizer.config.centered | False |
| dynamic | True |
| initial_scale | 32768.0 |
| dynamic_growth_steps | 2000 |
| training_precision | mixed_float16 |
- Task
- Text-to-Image
- Library
- keras
- License
- creativeml-openrail-m
- Languages
- en
- Created
- Mar 8, 2023
- Updated
- Mar 9, 2023