Instructions to use OPPOer/TLCMSDXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OPPOer/TLCMSDXL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OPPOer/TLCMSDXL", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,6 @@ library_name: diffusers
|
|
| 6 |
|
| 7 |
<p align="center">
|
| 8 |
📃 <a href="https://arxiv.org/html/2406.05768v5" target="_blank">Paper</a> •
|
| 9 |
-
🤗 <a href="https://huggingface.co/OPPOer/TLCM" target="_blank">Checkpoints</a>
|
| 10 |
</p>
|
| 11 |
|
| 12 |
<!-- **TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps** -->
|
|
@@ -25,4 +24,4 @@ global consistency across inter-segments through data-free consistency distillat
|
|
| 25 |
TLCM demonstrates a high level of flexibility by enabling adjustment of sampling steps within the range of 2 to 8 while still producing competitive outputs compared
|
| 26 |
to full-step approaches.
|
| 27 |
|
| 28 |
-
This is for SDXL-base LoRA.
|
|
|
|
| 6 |
|
| 7 |
<p align="center">
|
| 8 |
📃 <a href="https://arxiv.org/html/2406.05768v5" target="_blank">Paper</a> •
|
|
|
|
| 9 |
</p>
|
| 10 |
|
| 11 |
<!-- **TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps** -->
|
|
|
|
| 24 |
TLCM demonstrates a high level of flexibility by enabling adjustment of sampling steps within the range of 2 to 8 while still producing competitive outputs compared
|
| 25 |
to full-step approaches.
|
| 26 |
|
| 27 |
+
## This is for SDXL-base LoRA.
|