Text-to-Image
Diffusers
stable-diffusion
ip-adapter
face-id
identity-preservation
portrait
rishabh-in-code
Instructions to use RishabhInCode/TrueFace-Adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RishabhInCode/TrueFace-Adapter with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RishabhInCode/TrueFace-Adapter", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -50,11 +50,11 @@ To prove TrueFace-Adapter does not overfit to the training data, we tested it on
|
|
| 50 |
|
| 51 |
**Baseline (Standard IP-Adapter Zero-Shot):**
|
| 52 |
*Notice the loss of the square jawline, the alteration of the eye shape, and the complete loss of identity in the sketch (far right).*
|
| 53 |
-
:**
|
| 56 |
*The fine-tuned model strictly preserves the subject's deep-set eyes, specific jaw structure, and maintains high-fidelity likeness even in the charcoal sketch medium.*
|
| 57 |
-
:**
|
| 52 |
*Notice the loss of the square jawline, the alteration of the eye shape, and the complete loss of identity in the sketch (far right).*
|
| 53 |
+

|
| 54 |
|
| 55 |
**TrueFace-Adapter (Ours):**
|
| 56 |
*The fine-tuned model strictly preserves the subject's deep-set eyes, specific jaw structure, and maintains high-fidelity likeness even in the charcoal sketch medium.*
|
| 57 |
+

|
| 58 |
|
| 59 |
|
| 60 |
## Usage
|