Text-to-Image
Diffusers
flux
flux-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
standard
Model card auto-generated by SimpleTuner
Browse files
README.md
CHANGED
|
@@ -12,17 +12,7 @@ tags:
|
|
| 12 |
- template:sd-lora
|
| 13 |
- standard
|
| 14 |
inference: true
|
| 15 |
-
|
| 16 |
-
- text: 'unconditional (blank prompt)'
|
| 17 |
-
parameters:
|
| 18 |
-
negative_prompt: 'blurry, cropped, ugly'
|
| 19 |
-
output:
|
| 20 |
-
url: ./assets/image_0_0.png
|
| 21 |
-
- text: 'A secluded beach at sunset, where the sky is painted with hues of pink, orange, and gold. A couple sits close together on a soft blanket, surrounded by glowing lanterns gently swaying in the ocean breeze. The sound of waves softly crashing against the shore harmonizes with the melody of a string quartet playing in the distance. They share heartfelt laughter as they toast with sparkling champagne, their eyes reflecting the warmth of the setting sun. The moment feels timeless, as if the world exists only for their love, under the embrace of the stars beginning to twinkle above.'
|
| 22 |
-
parameters:
|
| 23 |
-
negative_prompt: 'blurry, cropped, ugly'
|
| 24 |
-
output:
|
| 25 |
-
url: ./assets/image_1_0.png
|
| 26 |
---
|
| 27 |
|
| 28 |
# maver1chh/jazzy2312
|
|
@@ -32,7 +22,7 @@ This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https:/
|
|
| 32 |
|
| 33 |
The main validation prompt used during training was:
|
| 34 |
```
|
| 35 |
-
A
|
| 36 |
```
|
| 37 |
|
| 38 |
|
|
@@ -47,7 +37,7 @@ A secluded beach at sunset, where the sky is painted with hues of pink, orange,
|
|
| 47 |
|
| 48 |
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
| 49 |
|
| 50 |
-
|
| 51 |
|
| 52 |
|
| 53 |
<Gallery />
|
|
@@ -59,7 +49,7 @@ You may reuse the base model text encoder for inference.
|
|
| 59 |
## Training settings
|
| 60 |
|
| 61 |
- Training epochs: 7
|
| 62 |
-
- Training steps:
|
| 63 |
- Learning rate: 0.0003
|
| 64 |
- Learning rate schedule: polynomial
|
| 65 |
- Warmup steps: 100
|
|
@@ -92,7 +82,7 @@ You may reuse the base model text encoder for inference.
|
|
| 92 |
- Crop style: None
|
| 93 |
- Crop aspect: None
|
| 94 |
- Used for regularisation data: No
|
| 95 |
-
###
|
| 96 |
- Repeats: 10
|
| 97 |
- Total number of images: 23
|
| 98 |
- Total number of aspect buckets: 1
|
|
@@ -124,7 +114,7 @@ adapter_id = 'maver1chh/maver1chh/jazzy2312'
|
|
| 124 |
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
|
| 125 |
pipeline.load_lora_weights(adapter_id)
|
| 126 |
|
| 127 |
-
prompt = "A
|
| 128 |
|
| 129 |
|
| 130 |
## Optional: quantise the model to save on vram.
|
|
|
|
| 12 |
- template:sd-lora
|
| 13 |
- standard
|
| 14 |
inference: true
|
| 15 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# maver1chh/jazzy2312
|
|
|
|
| 22 |
|
| 23 |
The main validation prompt used during training was:
|
| 24 |
```
|
| 25 |
+
A girl in light blue sits at the bar counter, holding an ice-cold wine glass and drinking alone on top of the Eiffel Tower, with a night view outside the window.. It features a close-up shot of her sitting by herself. She has long hair, wears glasses, faces away from the camera, and is wearing white shoes, black pants, a gray jacket, and a green scarf. with bright colors and a Paris night background featuring the Eiffel Tower. The composition is elegant, with the woman sitting on a high stool.
|
| 26 |
```
|
| 27 |
|
| 28 |
|
|
|
|
| 37 |
|
| 38 |
Note: The validation settings are not necessarily the same as the [training settings](#training-settings).
|
| 39 |
|
| 40 |
+
|
| 41 |
|
| 42 |
|
| 43 |
<Gallery />
|
|
|
|
| 49 |
## Training settings
|
| 50 |
|
| 51 |
- Training epochs: 7
|
| 52 |
+
- Training steps: 6001
|
| 53 |
- Learning rate: 0.0003
|
| 54 |
- Learning rate schedule: polynomial
|
| 55 |
- Warmup steps: 100
|
|
|
|
| 82 |
- Crop style: None
|
| 83 |
- Crop aspect: None
|
| 84 |
- Used for regularisation data: No
|
| 85 |
+
### jazz-768
|
| 86 |
- Repeats: 10
|
| 87 |
- Total number of images: 23
|
| 88 |
- Total number of aspect buckets: 1
|
|
|
|
| 114 |
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
|
| 115 |
pipeline.load_lora_weights(adapter_id)
|
| 116 |
|
| 117 |
+
prompt = "A girl in light blue sits at the bar counter, holding an ice-cold wine glass and drinking alone on top of the Eiffel Tower, with a night view outside the window.. It features a close-up shot of her sitting by herself. She has long hair, wears glasses, faces away from the camera, and is wearing white shoes, black pants, a gray jacket, and a green scarf. with bright colors and a Paris night background featuring the Eiffel Tower. The composition is elegant, with the woman sitting on a high stool."
|
| 118 |
|
| 119 |
|
| 120 |
## Optional: quantise the model to save on vram.
|