Flux LoRA Collections
Collection
Flux THE LoRA • 131 items • Updated • 32
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/CAnime-LoRA")
prompt = "CAnime, An animated portrait of a young man in a bright orange jacket with a light blue shirt underneath. The mans eyes are closed, and his lips are slightly parted. His hair is a vibrant orange, and he is wearing a pair of light blue jeans. The background is a pale blue, and there is a large circular blue circle in the background."
image = pipe(prompt).images[0]CAnime-LoRA
- Prompt
- CAnime, An animated portrait of a young man in a bright orange jacket with a light blue shirt underneath. The mans eyes are closed, and his lips are slightly parted. His hair is a vibrant orange, and he is wearing a pair of light blue jeans. The background is a pale blue, and there is a large circular blue circle in the background.
- Prompt
- CAnime, An animated image of a hamburger on a light blue background. The hamburger is a vibrant shade of pink, with a golden brown bun, and a thick layer of lettuce and cheese. The bun is adorned with a variety of colorful stripes, adding a pop of color to the scene. The sandwich is positioned in a circular fashion, with the top layer being the same shade as the bottom layer. There is a shadow of the hamburger cast on the ground below it.
- Prompt
- CAnime, Captured at eye-level on a vibrant day, a detailed detailed illustration of a mountain range is depicted. The mountains top is adorned with a white snow-capped peak, adding a touch of color to the scene. The sky is a deep blue, with a few wispy clouds in the distance. The sun is setting, casting a pink hue over the mountain, adding depth to the composition. The mountains are reflected in a body of water, creating a stunning contrast to the sky.
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/CAnime-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 | 21 & 2000 |
| Epoch | 12 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 13
Best Dimensions
- 1024 x 1024 (Default)
| Description |
|---|
| CAnime, Beautiful anime style illustration of a Cat, wearing vibrant flat colors on a blue background with a pastel color palette. Bright daylight lighting is used, yellowcore |
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/CAnime-LoRA"
trigger_word = "CAnime"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use CAnime 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
- 61
Model tree for prithivMLmods/CAnime-LoRA
Base model
black-forest-labs/FLUX.1-dev