Model card auto-generated by SimpleTuner

README.md

@@ -72,8 +72,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 1
-- Training steps: 2000
+- Training epochs: 2
+- Training steps: 2500
 - Learning rate: 0.0001
 - Effective batch size: 2
   - Micro-batch size: 2
@@ -115,7 +115,7 @@ You may reuse the base model text encoder for inference.
 ### garfield
 - Repeats: 0
 - Total number of images: 2206
-- Total number of aspect buckets: 1
+- Total number of aspect buckets: 4
 - Resolution: 512 px
 - Cropped: False
 - Crop style: None
@@ -126,87 +126,27 @@ You may reuse the base model text encoder for inference.
 
 
 ```python
-import argparse
 import torch
-from helpers.models.flux.pipeline import FluxPipeline as DiffusionPipeline
+from diffusers import DiffusionPipeline
 from lycoris import create_lycoris_from_weights
-from huggingface_hub import hf_hub_download
-
-def generate_image(pipeline, prompt, output_file, num_inference_steps, width, height, guidance_scale, seed, device):
-    # Set device
-    pipeline.to(device)
-
-    # Generate image
-    generator = torch.Generator(device=device).manual_seed(seed)
-    image = pipeline(
-        prompt=prompt,
-        num_inference_steps=num_inference_steps,
-        generator=generator,
-        width=width,
-        height=height,
-        guidance_scale=guidance_scale,
-    ).images[0]
-
-    # Save image
-    output_file = "output.png"
-    image.save(output_file, format="PNG")
-    print(f"Image saved as {output_file}")
-
-def main():
-    parser = argparse.ArgumentParser(description="Generate images using a custom diffusion pipeline with LoRA weights.")
-    parser.add_argument("--model_id", type=str, default='black-forest-labs/FLUX.1-dev', help="Model ID from Hugging Face Hub.")
-    parser.add_argument("--adapter_id", type=str, default='pytorch_lora_weights.safetensors', help="LoRA weights file.")
-    parser.add_argument("--lora_scale", type=float, default=1.0, help="Scale for LoRA weights.")
-    parser.add_argument("--output_file", type=str, default="output.png", help="Output file name for the generated image.")
-    parser.add_argument("--num_inference_steps", type=int, default=30, help="Number of inference steps.")
-    parser.add_argument("--guidance_scale", type=float, default=3.5, help="Guidance scale for the generation.")
-    parser.add_argument("--seed", type=int, default=1641421826, help="Random seed for reproducibility.")
-    parser.add_argument("--device", type=str, default='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu', help="Device to run the model on.")
-    
-    args = parser.parse_args()
-
-    # Load model and weights
-    hf_hub_download(repo_id="terminusresearch/flux-lokr-garfield-masked", filename=args.adapter_id, local_dir="./")
-    pipeline = DiffusionPipeline.from_pretrained(args.model_id, torch_dtype=torch.bfloat16)
-
-    # Apply LoRA weights
-    wrapper, _ = create_lycoris_from_weights(args.lora_scale, args.adapter_id, pipeline.transformer)
-    wrapper.merge_to()
-
-    print("Model loaded successfully. Ready to generate images.")
-    
-    while True:
-        user_input = input("Enter a prompt or 'quit' to exit: ")
-        if user_input.lower() == 'quit':
-            break
-
-        # Check for resolution command
-        if user_input.startswith("resolution:"):
-            resolution = user_input.split(":")[1]
-            width, height = map(int, resolution.split("x"))
-            print(f"Resolution set to {width}x{height}")
-            continue
-
-        prompt = user_input
-        output_file = args.output_file.replace(".png", f"_{prompt.replace(' ', '_')}.png")
-
-        # Use default or previously set resolution
-        width = locals().get('width', 1024)
-        height = locals().get('height', 1024)
-
-        generate_image(
-            pipeline=pipeline,
-            prompt=prompt,
-            output_file=output_file,
-            num_inference_steps=args.num_inference_steps,
-            width=width,
-            height=height,
-            guidance_scale=args.guidance_scale,
-            seed=args.seed,
-            device=args.device
-        )
-
-if __name__ == "__main__":
-    main()
+
+model_id = 'black-forest-labs/FLUX.1-dev'
+adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
+lora_scale = 1.0
+wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
+wrapper.merge_to()
+
+prompt = "A photo-realistic image of a cat"
+
+pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
+image = pipeline(
+    prompt=prompt,
+    num_inference_steps=20,
+    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
+    width=1776,
+    height=512,
+    guidance_scale=3.0,
+).images[0]
+image.save("output.png", format="PNG")
 ```