Kontext Dev LoRAs
Collection
Collection of Kontext Dev LoRAs by fal • 30 items • Updated • 35
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("fal/Youtube-Thumbnails-Kontext-Dev-LoRA")
prompt = "Generate youtube thumbnails using text \"EPIC FAIL.\""
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]Youtube Thumbnails Kontext Dev LoRA
- Prompt
- Generate youtube thumbnails using text "EPIC FAIL."
- Prompt
- Generate youtube thumbnails using text "MIND BLOWN!"
- Prompt
- Generate youtube thumbnails using text "CAN'T BELIEVE IT!"
- Prompt
- Generate youtube thumbnails using text "fal.ai is best.". Hands around his head.
Model description
Works best at resolution 1536x1024 input images (works on other resolutions as well)
Recommended lora scale: 0.4-0.5
Trigger phrase
Generate youtube thumbnails using text "Your text"
Download model
Weights for this model are available in Safetensors format.
Training at fal.ai
Training was done using fal.ai/models/fal-ai/flux-kontext-trainer/playground.
- Downloads last month
- 26
Model tree for fal/Youtube-Thumbnails-Kontext-Dev-LoRA
Base model
black-forest-labs/FLUX.1-Kontext-dev