Instructions to use xcreates/GLM-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xcreates/GLM-Image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xcreates/GLM-Image", 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
- Draw Things
- DiffusionBee
Upload complete model
Browse files
processor/chat_template.jinja
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- for m in messages -%}
|
| 2 |
+
{%- if m.content is string -%}
|
| 3 |
+
{{ m.content }}
|
| 4 |
+
{%- else -%}
|
| 5 |
+
{%- for item in m.content -%}
|
| 6 |
+
{%- if item.type == 'image' or item.get('image') is not none -%}
|
| 7 |
+
<|dit_token_16384|><|image|><|dit_token_16385|>
|
| 8 |
+
{%- elif item.type == 'text' -%}
|
| 9 |
+
{{ item.text }}
|
| 10 |
+
{%- endif -%}
|
| 11 |
+
{%- endfor -%}
|
| 12 |
+
{%- endif -%}
|
| 13 |
+
{%- endfor -%}
|