metadata

tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
  - text: Kalamkari textile pattern, 4K
    output:
      url: images/tp3.png
  - text: Ikat textile pattern, 4K
    output:
      url: images/tp4.png
  - text: Floral textile pattern, 4K
    output:
      url: images/tp5.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: textile pattern
license: apache-2.0

Canopus-Textile-Patterns

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	30
Epoch	09	Save Every N Epochs	1

Total Steps: 1080

SETTING-UP

    pipe = StableDiffusionXLPipeline.from_pretrained(
        "-------------xxxxxxxxx----------",
        torch_dtype=torch.float16,
        use_safetensors=True,
    )
                    (or)
-----------------------------------------------------------
    pipe = StableDiffusionXLPipeline.from_pretrained(
        "stabilityai/stable-diffusion-xl-base-1.0",
        torch_dtype=torch.float16,
        use_safetensors=True,
    )
    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
    
    pipe.load_lora_weights("prithivMLmods/Canopus-Textile-Pattern-adp-LoRA", weight_name="Canopus-Textile-Pattern-adp-LoRA.safetensors", adapter_name="tpl")
    pipe.set_adapters("tpl")
    pipe.to("cuda")

Trigger prompts

Kalamkari textile pattern, 4K


Ikat textile pattern, 4K


Floral textile pattern, 4K

Parameter	Value
Prompt	Floral textile pattern, 4K
Sampler	euler

Trigger words

You should use textile pattern to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.