--- 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 ```py 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](/prithivMLmods/Canopus-Textile-Pattern-adp-LoRA/tree/main) them in the Files & versions tab.