Flux LoRA Collections
Collection
Flux THE LoRA • 131 items • Updated • 33
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA")
prompt = "frosted GC, a pristine white jar, adorned with a silver lid, is adorned with the words \"Spirulina\" in bold black lettering. The jar is set against a light blue backdrop, creating a stark contrast to the jars contents. A barcode is visible on the jar, adding a pop of color to the composition."
image = pipe(prompt).images[0]Flux.1-Dev-Frosted-Container-LoRA
- Prompt
- frosted GC, a pristine white jar, adorned with a silver lid, is adorned with the words "Spirulina" in bold black lettering. The jar is set against a light blue backdrop, creating a stark contrast to the jars contents. A barcode is visible on the jar, adding a pop of color to the composition.
- Prompt
- frosted GC, A medium shot of a white jar with a yellow lid. The jar has the words "Yellow" and "Fish Oil Bottle Mockup" written on it in black letters. There is a white background behind the jar.
- Prompt
- frosted GC, a small, gray bottle with a black cap is seen against a stark white backdrop. The bottles label, "Cellular Nutrition mitopure" is prominently displayed in the center of the frame, with the words "Time-line" written in white font on the right side of the bottle. The label also includes the number "60" and "50" in the bottom left corner.
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
Model description
prithivMLmods/Flux.1-Dev-Frosted-Container-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 | 14 & 2200 |
| Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 16
Best Dimensions
- 768 x 1024 (Best)
- 1024 x 1024 (Default)
Setting Up
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 = "prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA"
trigger_word = "frosted GC"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Other Sample Image
Trigger words
You should use frosted GC to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 52
Model tree for prithivMLmods/Flux.1-Dev-Frosted-Container-LoRA
Base model
black-forest-labs/FLUX.1-dev