prithivMLmods's picture
Update README.md
26b93e7 verified
|
raw
history blame
4.22 kB
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Creative Stocks, A flat lay of four neatly folded blue fabric rolls arranged in a square pattern. Each roll has a white label reading "COMFY-COTTON" with a minimalist logo of a cotton plant. The backdrop is a soft beige fabric.'
output:
url: images/1.png
- text: 'Creative Stocks, a medium-sized cardboard box is positioned against a stark white backdrop. The box is adorned with black text that reads "HOCUME 2MO RESERVED" and "MOD SOCKS". The boxs design features a blue sock and a yellow sock. The text is written in a bold, black font.'
output:
url: images/2.png
- text: 'Creative Stocks, A medium shot of a brown cardboard box with the words "SCHROBELER" written in green on the top of the box. The box is placed on a white wooden surface. There is a yellow label on the box with a man and a dog on it. The man is wearing a yellow shirt and a hat. The dog is holding a black bottle with a black cap. The bottle has a black label with white letters that read "LEKKER" on the bottom of it.'
output:
url: images/3.png
- text: 'Creative Stocks, Captured at eye-level on a vibrant green backdrop, two red boxes, each with the word "Tomatier" written in white on the left side of the box. The box on the right side is labeled "Snack" in black letters, while the box in the middle has "TOMATIER" written on it in white letters. The boxes are identical, with the same design as the one on the bottom left corner. Each box has a black design on it, adding a pop of color to the otherwise monochromatic image.'
output:
url: images/4.png
- text: 'Creative Stocks, A stack of gray aluminum cans arranged neatly on a wooden table. Each can is labeled with the word "FUEL+BOOST" in bold red letters and features a small graphic of a lightning bolt. The background is softly blurred, showcasing warm orange tones.'
output:
url: images/5.png
- text: 'Creative Stocks, A medium shot of a kraft paper bag with the words "FRESHLY ROASTED BEANS" in bold green letters. The bag has a clear window revealing coffee beans inside. It is placed on a white marble surface with a small potted plant in the blurred background.'
output:
url: images/6.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Creative Stocks
license: apache-2.0
---
![sdfg.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/wvnRvvCYSPPcyFX0Gfdtu.png)
<Gallery />
# Model description for Flux-Creative-Stocks-LoRA
Image Processing Parameters
| Parameter | Value | Parameter | Value |
|---------------------------|--------|---------------------------|--------|
| LR Scheduler | constant | Noise Offset | 0.03 |
| Optimizer | AdamW | Multires Noise Discount | 0.1 |
| Network Dim | 64 | Multires Noise Iterations | 10 |
| Network Alpha | 32 | Repeat & Steps | 19 & 2370 |
| Epoch | 16 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 24 [ Raw 8-bit ]
## Best Dimensions & Inference
| **Dimensions** | **Aspect Ratio** | **Recommendation** |
|-----------------|------------------|---------------------------|
| 1280 x 832 | 3:2 | Best |
| 1024 x 1024 | 1:1 | Default |
### Inference Range
- **Recommended Inference Steps:** 30–35
## Setting Up
```python
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-Creative-Stocks-LoRA"
trigger_word = "Creative Stocks"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
```
## Trigger words
You should use `Creative Stocks` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/strangerzonehf/Flux-Creative-Stocks-LoRA/tree/main) them in the Files & versions tab.