coreml-community/coreml-Stable_Diffusion_PaperCut_Model
9
1---2license: creativeml-openrail-m3thumbnail: "https://huggingface.co/coreml/coreml-anything-v3-1/resolve/main/example-images/thumbnail.png"4language:5- en6tags:7- coreml8- stable-diffusion9- stable-diffusion-diffusers10---11 12# Core ML Converted Model13 14This model was converted to Core ML for use on Apple Silicon devices by following Apple's instructions [here](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).<br>15Provide the model to an app such as [Mochi Diffusion](https://github.com/godly-devotion/MochiDiffusion) to generate images.<br>16 17`split_einsum` version is compatible with all compute unit options including Neural Engine.<br>18`original` version is only compatible with CPU & GPU option.19 20# 🧩 Paper Cut model V121This is the fine-tuned Stable Diffusion model trained on Paper Cut images.22 23Use **PaperCut** in your prompts.24 25### Sample images:262728Based on StableDiffusion 1.5 model29 30### 🧨 Diffusers31 32This model can be used just like any other Stable Diffusion model. For more information,33please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).34 35You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().36 37```python38from diffusers import StableDiffusionPipeline39import torch40 41model_id = "Fictiverse/Stable_Diffusion_PaperCut_Model"42pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)43pipe = pipe.to("cuda")44 45prompt = "PaperCut R2-D2"46image = pipe(prompt).images[0]47 48image.save("./R2-D2.png")49```50 51### ✨ Community spotlight :52@PiyarSquare :53[](https://www.youtube.com/watch?v=wQWHnZlxFj8)