Instructions to use pinecoresystems/Ming-Image-0.1-Design with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use pinecoresystems/Ming-Image-0.1-Design with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("pinecoresystems/Ming-Image-0.1-Design", 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
Upload mlp/config.json with huggingface_hub
Browse files- mlp/config.json +17 -0
mlp/config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"use_identity_mlp": true,
|
| 3 |
+
"use_vlm_directvlm_condition": true,
|
| 4 |
+
"use_learnable_token_condition": true,
|
| 5 |
+
"diffusion_c_input_dim": 2560,
|
| 6 |
+
"text_encoder_norm": false,
|
| 7 |
+
"connector_norm": false,
|
| 8 |
+
"img_gen_scales": [
|
| 9 |
+
16
|
| 10 |
+
],
|
| 11 |
+
"selected_hidden_states_layers": [
|
| 12 |
+
5,
|
| 13 |
+
12,
|
| 14 |
+
20
|
| 15 |
+
],
|
| 16 |
+
"diffusion_inner_dim": 3840
|
| 17 |
+
}
|