Instructions to use mirroring/civitai_mirror with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mirroring/civitai_mirror with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("mirroring/civitai_mirror", torch_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
Commit ·
7d130d4
1
Parent(s): 1af04d2
Upload /models/incoming/headback-lora.txt with huggingface_hub
Browse files
models/incoming/headback-lora.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Dataset used tags from WD1.4 tagger, with "head back" at the front of each tag list. Trained for 3000 steps with 15 images (there isn't much of this pose). Higher strength will guarantee the pose, lower strength will keep artsyle and other prompt factors, but may sometimes cause the girl to not look back fully.
|