Pepeline error in Colab

[Amit71965]

For below code:

Step 5: Load the base model and LoRA weights

from diffusers import DiffusionPipeline

import torch

print(“Loading base FLUX.1-dev model…”)

Load the base model

pipe = DiffusionPipeline.from_pretrained( #This is the line where I’m getting an error

“black-forest-labs/FLUX.1-dev”,

torch_dtype=torch.float16,

use_safetensors=True,

variant=“fp16”

)

Move the model to GPU for faster processing

pipe = pipe.to(“cuda”)

Load the LoRA weights

print(“Loading and applying LoRA weights from Amit71965/ai-amit…”)

pipe.load_lora_weights(“Amit71965/ai-amit”)

Optional: Test the model with a sample prompt

test_prompt = “Amit in a suit, professional portrait, high quality, detailed”

print(f"Generating a test image with prompt: ‘{test_prompt}’")

test_image = pipe(test_prompt).images[0]

test_image.save(os.path.join(base_dir, “test_image.png”))

print(f"Test image saved to {os.path.join(base_dir, ‘test_image.png’)}")

For Step 5 cell code, After running the cell I’m getting an error. Which is also attached as a screenshot.

How do I resolve this issue. I’m trying to lead this models and then perform quantisation and then convert it to CoreML to embed in iOS Application.

[John6666]

Try this.

# Load the base model
pipe = DiffusionPipeline.from_pretrained( #This is the line where I’m getting an error
   "black-forest-labs/FLUX.1-dev",
    torch_dtype=torch.float16,
    use_safetensors=True,
    #variant=“fp16” # <= Not required in this case. Use this when you want to load a file that is named .fp16.safetensors
)