Instructions to use zai-org/GLM-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/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("zai-org/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] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Add VDEBench evaluation results
#31
by hongzhuyi - opened
- .eval_results/vdebench.yaml +18 -0
.eval_results/vdebench.yaml
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: hongzhuyi/VDEBench
|
| 3 |
+
task_id: local
|
| 4 |
+
value: 0.459
|
| 5 |
+
source:
|
| 6 |
+
url: https://huggingface.co/datasets/hongzhuyi/VDEBench/blob/main/results/2026-11-05/glm_image/results.json
|
| 7 |
+
name: VDEBench full evaluation (2026-11-05)
|
| 8 |
+
user: hongzhuyi
|
| 9 |
+
notes: "local setting, n=3,506, PaddleOCR-VL; mean of block-pooled IoU, CDM, BLEU-4 and TEDS; round half up to 3 decimals"
|
| 10 |
+
- dataset:
|
| 11 |
+
id: hongzhuyi/VDEBench
|
| 12 |
+
task_id: global
|
| 13 |
+
value: 0.453
|
| 14 |
+
source:
|
| 15 |
+
url: https://huggingface.co/datasets/hongzhuyi/VDEBench/blob/main/results/2026-11-05/glm_image/results.json
|
| 16 |
+
name: VDEBench full evaluation (2026-11-05)
|
| 17 |
+
user: hongzhuyi
|
| 18 |
+
notes: "global setting, n=3,506, PaddleOCR-VL; mean of block-pooled IoU, CDM, BLEU-4 and TEDS; round half up to 3 decimals"
|