Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,52 @@ license: creativeml-openrail-m
|
|
| 22 |
|
| 23 |
<Gallery />
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Trigger words
|
| 27 |
|
|
|
|
| 22 |
|
| 23 |
<Gallery />
|
| 24 |
|
| 25 |
+
**The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.**
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
**prithivMLmods/Uncoloured-Polygon-Flux-LoRA**
|
| 30 |
+
|
| 31 |
+
Image Processing Parameters
|
| 32 |
+
|
| 33 |
+
| Parameter | Value | Parameter | Value |
|
| 34 |
+
|---------------------------|--------|---------------------------|--------|
|
| 35 |
+
| LR Scheduler | constant | Noise Offset | 0.03 |
|
| 36 |
+
| Optimizer | AdamW | Multires Noise Discount | 0.1 |
|
| 37 |
+
| Network Dim | 64 | Multires Noise Iterations | 10 |
|
| 38 |
+
| Network Alpha | 32 | Repeat & Steps | 25 & 1.5K |
|
| 39 |
+
| Epoch | 14 | Save Every N Epochs | 1 |
|
| 40 |
+
|
| 41 |
+
Labeling: florence2-en(natural language & English)
|
| 42 |
+
|
| 43 |
+
Total Images Used for Training : 25+ [ Hi-RES ]
|
| 44 |
+
|
| 45 |
+
## Data Source
|
| 46 |
+
|
| 47 |
+
https://search.muz.li/
|
| 48 |
+
|
| 49 |
+
## Sample Image + Prompt
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
| **Prompt** |
|
| 54 |
+
|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 55 |
+
| Closeup of Lucia stands atop a skyscraper, elegant and hot, cool detailing, the bustling city below illuminated by neon lights and the sounds of nightlife. Her dark hair billows in the wind, and her striking features are accentuated by the glow of the moonlight. Dressed in a sleek, stylish outfit, she gazes thoughtfully over the edge, her piercing gaze reflecting the determination and resilience that define her character. In one hand, she holds a small gadget, a symbol of her tech-savvy nature and resourcefulness in the vibrant chaos of the GTA 6 world. |
|
| 56 |
+
|
| 57 |
+
## Setting Up
|
| 58 |
+
```
|
| 59 |
+
import torch
|
| 60 |
+
from pipelines import DiffusionPipeline
|
| 61 |
+
|
| 62 |
+
base_model = "black-forest-labs/FLUX.1-dev"
|
| 63 |
+
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
|
| 64 |
+
|
| 65 |
+
lora_repo = "prithivMLmods/Castor-Concept-Gta6-Character-Design"
|
| 66 |
+
trigger_word = "Jason, Lucia, GTA 6" # Leave trigger_word blank if not used.
|
| 67 |
+
pipe.load_lora_weights(lora_repo)
|
| 68 |
+
|
| 69 |
+
device = torch.device("cuda")
|
| 70 |
+
pipe.to(device)
|
| 71 |
|
| 72 |
## Trigger words
|
| 73 |
|