Text-to-Image
PEFT
Safetensors
Diffusers
English
lora
flux
reinforcement-learning
face-diversity
multi-human
Instructions to use Qualcomm-AI-Research/disco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Qualcomm-AI-Research/disco with PEFT:
Task type is invalid.
- Diffusers
How to use Qualcomm-AI-Research/disco with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Qualcomm-AI-Research/disco") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -108,7 +108,7 @@ pipe.transformer = PeftModel.from_pretrained(
|
|
| 108 |
pipe.transformer = pipe.transformer.merge_and_unload()
|
| 109 |
|
| 110 |
image = pipe(
|
| 111 |
-
"Six people on a campus walkway,
|
| 112 |
"fine detail, lifelike rendering, diversity in ethnicity.",
|
| 113 |
height=1024,
|
| 114 |
width=1024,
|
|
|
|
| 108 |
pipe.transformer = pipe.transformer.merge_and_unload()
|
| 109 |
|
| 110 |
image = pipe(
|
| 111 |
+
"A stunning close-up of Six people on a campus walkway, clear faces visible, "
|
| 112 |
"fine detail, lifelike rendering, diversity in ethnicity.",
|
| 113 |
height=1024,
|
| 114 |
width=1024,
|