Instructions to use warp-ai/wuerstchen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use warp-ai/wuerstchen with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("warp-ai/wuerstchen", 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
Upload folder using huggingface_hub
Browse files- vqgan/config.json +3 -3
vqgan/config.json
CHANGED
|
@@ -2,11 +2,11 @@
|
|
| 2 |
"_class_name": "VQModelPaella",
|
| 3 |
"_diffusers_version": "0.20.0.dev0",
|
| 4 |
"bottleneck_blocks": 12,
|
| 5 |
-
"
|
| 6 |
-
"c_latent": 4,
|
| 7 |
-
"codebook_size": 8192,
|
| 8 |
"in_channels": 3,
|
|
|
|
| 9 |
"levels": 2,
|
|
|
|
| 10 |
"out_channels": 3,
|
| 11 |
"scale_factor": 0.3764,
|
| 12 |
"up_down_scale_factor": 2
|
|
|
|
| 2 |
"_class_name": "VQModelPaella",
|
| 3 |
"_diffusers_version": "0.20.0.dev0",
|
| 4 |
"bottleneck_blocks": 12,
|
| 5 |
+
"embed_dim": 384,
|
|
|
|
|
|
|
| 6 |
"in_channels": 3,
|
| 7 |
+
"latent_channels": 4,
|
| 8 |
"levels": 2,
|
| 9 |
+
"num_vq_embeddings": 8192,
|
| 10 |
"out_channels": 3,
|
| 11 |
"scale_factor": 0.3764,
|
| 12 |
"up_down_scale_factor": 2
|