Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,59 @@ license: creativeml-openrail-m
|
|
| 24 |
<Gallery />
|
| 25 |
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
## Trigger words
|
| 28 |
|
| 29 |
You should use `Photo Shoot` to trigger the image generation.
|
|
|
|
| 24 |
<Gallery />
|
| 25 |
|
| 26 |
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
Canopus-Photo-Shoot-Mini-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 | 27 |
|
| 39 |
+
| Epoch | 20 | Save Every N Epochs | 1 |
|
| 40 |
+
|
| 41 |
+
## SETTING-UP
|
| 42 |
+
|
| 43 |
+
```py
|
| 44 |
+
pipe = StableDiffusionXLPipeline.from_pretrained(
|
| 45 |
+
"-------------xxxxxxxxx----------",
|
| 46 |
+
torch_dtype=torch.float16,
|
| 47 |
+
use_safetensors=True,
|
| 48 |
+
)
|
| 49 |
+
(or)
|
| 50 |
+
-----------------------------------------------------------
|
| 51 |
+
pipe = StableDiffusionXLPipeline.from_pretrained(
|
| 52 |
+
"stabilityai/stable-diffusion-xl-base-1.0",
|
| 53 |
+
torch_dtype=torch.float16,
|
| 54 |
+
use_safetensors=True,
|
| 55 |
+
)
|
| 56 |
+
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
|
| 57 |
+
|
| 58 |
+
pipe.load_lora_weights("prithivMLmods/Canopus-Photo-Shoot-Mini-LoRA", weight_name="Canopus-Photo-Shoot-Mini-LoRA.safetensors", adapter_name="photo")
|
| 59 |
+
pipe.set_adapters("photo")
|
| 60 |
+
pipe.to("cuda")
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
## Trigger prompts
|
| 65 |
+
|
| 66 |
+
Photography, upper body, yellow hue, woman model, solid yellow backdrop, yellow eyes detailing, using a camera setup that mimics a large aperture, f/1.4 --ar 9:16 --style raw
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
Young red-haired man, in turtleneck shirt, gold color, dynamic pose, side view, light background, front lighting, medium shot, high quality photo --ar 2:3 --v 5
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
A photo of an attractive man in his thirties, wearing a black coat and yellow scarf with a brown pattern inside a building talking on a phone standing near a modern glass skyscraper in London, shot from below looking up at him in the style of street photography, cinematic. --ar 85:128 --v 6.0 --style raw
|
| 73 |
+
|
| 74 |
+
| Parameter | Value |
|
| 75 |
+
|-----------------|---------------------------------------------------------------------------------------|
|
| 76 |
+
| Prompt | Young red-haired man, in turtleneck shirt, gold color, dynamic pose, side view, light background, front lighting, medium shot, high quality photo --ar 2:3 --v 5 |
|
| 77 |
+
| Sampler | euler |
|
| 78 |
+
|
| 79 |
+
|
| 80 |
## Trigger words
|
| 81 |
|
| 82 |
You should use `Photo Shoot` to trigger the image generation.
|