Unconditional Image Generation
Diffusers
TensorBoard
Safetensors
PyTorch
DDPMPipeline
diffusion-models-class
Instructions to use afshr/cam_normal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use afshr/cam_normal with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("afshr/cam_normal", 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
Epoch 1
Browse files
logs/train_example/events.out.tfevents.1721400155.b936aac3fa4b.1469.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1df1ec1c0c233e1cfa47ccd4463413a4f4df659b30be6dffb90c67c516115b9
|
| 3 |
+
size 3332
|
samples/0001.png
ADDED
|
unet/config.json
CHANGED
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"num_train_timesteps": null,
|
| 34 |
"out_channels": 3,
|
| 35 |
"resnet_time_scale_shift": "default",
|
| 36 |
-
"sample_size":
|
| 37 |
"time_embedding_type": "positional",
|
| 38 |
"up_block_types": [
|
| 39 |
"UpBlock2D",
|
|
|
|
| 33 |
"num_train_timesteps": null,
|
| 34 |
"out_channels": 3,
|
| 35 |
"resnet_time_scale_shift": "default",
|
| 36 |
+
"sample_size": 16,
|
| 37 |
"time_embedding_type": "positional",
|
| 38 |
"up_block_types": [
|
| 39 |
"UpBlock2D",
|
unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 143020060
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58ab73f5eabc4fa3a4e2cbf6236dbe0246c72694601768e12eac205c0eea33ee
|
| 3 |
size 143020060
|