Instructions to use Qwen/Qwen-Image-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Qwen/Qwen-Image-2.1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2.1", 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
Update to 0919 release checkpoint; fix vae scale_factor_spatial=16, remove transformer causal_block
Browse files
transformer/config.json
CHANGED
|
@@ -15,6 +15,5 @@
|
|
| 15 |
"patch_size": 1,
|
| 16 |
"mlp_ratio": 3,
|
| 17 |
"eps": 1e-06,
|
| 18 |
-
"causal_condition": true
|
| 19 |
-
|
| 20 |
-
}
|
|
|
|
| 15 |
"patch_size": 1,
|
| 16 |
"mlp_ratio": 3,
|
| 17 |
"eps": 1e-06,
|
| 18 |
+
"causal_condition": true
|
| 19 |
+
}
|
|
|
transformer/diffusion_pytorch_model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9968332504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6bc2d641e67bf277895ea8777141044a38f3edb7101bc469b2961dd7c36b4b
|
| 3 |
size 9968332504
|
transformer/diffusion_pytorch_model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4261951904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3aaf234dcbe128530479735854a346b5e3e66283b7c11db56f836bbd1c13ebaa
|
| 3 |
size 4261951904
|
vae/config.json
CHANGED
|
@@ -149,7 +149,7 @@
|
|
| 149 |
"num_res_blocks": 2,
|
| 150 |
"out_channels": 4,
|
| 151 |
"patch_size": null,
|
| 152 |
-
"scale_factor_spatial":
|
| 153 |
"scale_factor_temporal": 8,
|
| 154 |
"temperal_downsample": [
|
| 155 |
false,
|
|
@@ -158,4 +158,4 @@
|
|
| 158 |
true
|
| 159 |
],
|
| 160 |
"z_dim": 64
|
| 161 |
-
}
|
|
|
|
| 149 |
"num_res_blocks": 2,
|
| 150 |
"out_channels": 4,
|
| 151 |
"patch_size": null,
|
| 152 |
+
"scale_factor_spatial": 16,
|
| 153 |
"scale_factor_temporal": 8,
|
| 154 |
"temperal_downsample": [
|
| 155 |
false,
|
|
|
|
| 158 |
true
|
| 159 |
],
|
| 160 |
"z_dim": 64
|
| 161 |
+
}
|