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("ms2stationthis/drifella")
prompt = "drifella, This is a digital collage featuring a stylized, anthropomorphic gray cat with large blue eyes, a red nose, and a yellow headband. The cat has a cigarette in its mouth and is wearing a white shirt with \"Licker is the big movie\" text. The background is black with musical notes overlaying the image. To the left, a small brown dog with a sad expression and a black ear is visible. In the bottom right, a hand holds a blue water bottle with a red label. The overall style is a mix of cartoonish and surreal, with a in the style of grungy, urban aesthetic."
image = pipe(prompt).images[0]drifella
This LoRA model generates vibrant digital collages featuring stylized anthropomorphic cats, characterized by large expressive eyes and quirky accessories like headbands and cigarettes. The compositions often incorporate bold text and musical elements against striking backgrounds, emphasizing a playful and artistic visual style.
Trigger word: drifella
Sample Outputs
 |
 |
| drifella, This is a digital collage featuring a stylized, an... | drifella, This digital collage features a surreal, anthropom... |
 |
 |
| drifella, This is a digitally altered photograph featuring a... | drifella, This digital artwork features a surreal, cartoonis... |
Usage
ComfyUI
- Download the
.safetensorsfile from the Files tab - Place in
ComfyUI/models/loras/ - Use the Load LoRA node with strength
0.8-1.0 - Include
drifellain your prompt
Diffusers
import torch
from diffusers import FluxPipeline
pipe = FluxPipeline.from_pretrained(
"black-forest-labs/FLUX.1-dev",
torch_dtype=torch.bfloat16
)
pipe.load_lora_weights("ms2stationthis/drifella")
pipe.to("cuda")
image = pipe(
prompt="drifella portrait, soft lighting, detailed",
guidance_scale=3.5-4.0,
num_inference_steps=20-30,
generator=torch.Generator("cuda").manual_seed(42)
).images[0]
image.save("output.png")
Recommended Settings
| Parameter | Value |
|---|---|
| LoRA Strength | 0.8-1.0 |
| Guidance Scale | 3.5-4.0 |
| Inference Steps | 20-30 |
| Resolution | 1024x1024 |
Example Prompts
drifella this is a digital collage featuring a stylizeddrifella anthropomorphic gray cat with large blue eyesdrifella a red nosedrifella with a in the style of grungy
Training Details
- Base model: black-forest-labs/FLUX.1-dev
- Training steps: 4000
- Trigger word:
drifella - Network: LoRA rank 32, alpha 32
- Optimizer: adamw8bit, lr 1e-4
- Precision: float16
- Resolution: 512, 768, 1024 (multi-res bucketed)
About
Trained using StationThis — an AI creative platform powered by $MS2. Train your own LoRAs via @stationthisbot on Telegram.
Generated by StationThis Training Pipeline
Model tree for ms2stationthis/drifella
Base model
black-forest-labs/FLUX.1-dev