--- tags: - text-to-image - stable-diffusion - lora - diffusers - template:sd-lora - StableDiffusionXLPipeline - Inference Endpoints - sdxl widget: - text: >- A black Ford Mustang was photographed on the side of an abandoned road in British Columbia, Canada surrounded by trees and grass. The car is driving fast down the dirt road at sunset. Light beams shine from its headlights. Shot in the style of Peter Lindbergh for Aman Resorts --ar 85:128 --v 6.0 --style raw output: url: images/c1.png - text: >- A cars headlights illuminate part of its body. This scene creates a tranquil atmosphere with soft lighting and warm tones, in the style of minimalism. --ar 85:128 --v 6.0 --style raw output: url: images/c2.png - text: >- An vector illustration of an old car on the road, in a retro poster style with orange and yellow colors, featuring vintage cars from past years, set against a backdrop of mountains, trees, clouds, and sunset. The scene captures a sense of adventure as if moving through time in a classic automotive journey. Its an appealing design that would be perfect for travel-themed projects or packaging materials related to vintage vehicles, in the style of retro posters. --ar 128:89 --v 6.0 --style raw output: url: images/c3.png base_model: stabilityai/stable-diffusion-xl-base-1.0 instance_prompt: Cars, Concept Cars license: creativeml-openrail-m --- # Car Model ## Model description Cars-Model / Concept Cars 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 | 20 | | Epoch | 20 | Save Every N Epochs | 1 | ## 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/Canes-Cars-Model-LoRA", weight_name="Canes-Cars-Model-LoRA.safetensors", adapter_name="car") pipe.set_adapters("car") pipe.to("cuda") ``` ## Trigger prompts A black Ford Mustang was photographed on the side of an abandoned road in British Columbia, Canada surrounded by trees and grass. The car is driving fast down the dirt road at sunset. Light beams shine from its headlights. Shot in the style of Peter Lindbergh for Aman Resorts --ar 85:128 --v 6.0 --style raw A car's headlights illuminate part of its body. This scene creates a tranquil atmosphere with soft lighting and warm tones, in the style of minimalism. --ar 85:128 --v 6.0 --style raw An vector illustration of an old car on the road, in a retro poster style with orange and yellow colors, featuring vintage cars from past years, set against a backdrop of mountains, trees, clouds, and sunset. The scene captures a sense of adventure as if moving through time in a classic automotive journey. It's an appealing design that would be perfect for travel-themed projects or packaging materials related to vintage vehicles, in the style of retro posters. --ar 128:89 --v 6.0 --style raw | Parameter | Value | |-----------------|---------------------------------------------------------------------------------------| | Prompt | A car's headlights illuminate part of its body. This scene creates a tranquil atmosphere with soft lighting and warm tones, in the style of minimalism. --ar 85:128 --v 6.0 --style raw | | Sampler | euler | ## Trigger words You should use `Cars` to trigger the image generation. You should use `Concept Cars` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/prithivMLmods/Canes-Cars-Model-LoRA/tree/main) them in the Files & versions tab.