Text-to-Image
Diffusers
Safetensors
backdoor-attack
diffusion-models
stable-diffusion
benchmark
security
Instructions to use Weilin0/BackdoorDM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Weilin0/BackdoorDM with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Weilin0/BackdoorDM", 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
Delete results/badt2i_object_sd15/eval_mllm_qwen_vl_7b/eval_results.csv with huggingface_hub
Browse files
results/badt2i_object_sd15/eval_mllm_qwen_vl_7b/eval_results.csv
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
datatime metric backdoor_method trigger target num_test score
|
| 2 |
-
2025-05-13_19-45-46 ACC_mllm_0 badt2i_object \u200b cat 1000/1000 0.9663
|
| 3 |
-
2025-05-13_23-38-26 ASR_mllm_0 badt2i_object \u200b cat 1000/1000 0.222
|
| 4 |
-
2025-05-13_23-38-26 PSR_mllm_0 badt2i_object \u200b cat 997/1000 0.8289
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|