Instructions to use Falah/sdarchitecturalv1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Falah/sdarchitecturalv1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Falah/sdarchitecturalv1", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
| license: openrail | |
| language: | |
| - en | |
| # Architecture Based Stable Diffusion version.1.5 Model | |
| ## Models AI Art Style: Text-to-Image Generation with Stable Diffusion | |
| ## Overview | |
| The Models AI Art Style is a text-to-image generation model built on the Hugging Face Hub. It utilizes the Stable Diffusion architecture | |
| to convert textual descriptions into visually appealing images. This repository contains the implementation for the Dreambooth model (SDarchitecturalV1), which has been trained by Falah using TheLastBen's fast-DreamBooth notebook. | |
| ## License | |
| This project is licensed under the CreativeML OpenRail-M License. For more details, please refer to the [LICENSE](LICENSE) file. | |
| ## Tags | |
| - Text-to-Image | |
| - Stable Diffusion | |
| ## Model Details | |
| The Dreambooth model (SDarchitecturalV1) has been trained by Falah and leverages TheLastBen's fast-DreamBooth notebook for training. This combination of architecture and training notebook results in impressive text-to-image generation capabilities. | |
| ## Text-to-Image Architecture | |
| The text-to-image generation process involves the following steps: | |
| 1. **Text Prompt**: Input a textual description or prompt that conveys the desired image's content and style. | |
| 2. **Model Inference**: The Dreambooth model (SDarchitecturalV1) uses the Stable Diffusion architecture to transform the text prompt into image features. | |
| 3. **Image Generation**: The generated image features are transformed into a coherent image by the model. | |
|  | |
| ## Application: Modern Home Images | |
| The Models AI Art Style excels at generating images of modern home designs based on text prompts. Whether you need images of sleek apartments, minimalist interiors, or contemporary architectural concepts, the model can bring your ideas to life. | |
| ### Sample Text Prompts for Modern Homes: | |
| 1. "A spacious living room with floor-to-ceiling windows and minimalist furniture." | |
| 2. "A modern kitchen with stainless steel appliances and an open-concept layout." | |
| 3. "An elegant bedroom with a sleek king-sized bed and soft ambient lighting." | |
| Simply provide a text prompt like the ones above, and the Models AI Art Style will produce stunning images of modern home environments that match your description. | |
| .png) | |
| .png) | |
|  | |
|  | |
| .png) | |
| ## Testing | |
| To test the concept of text-to-image generation using the Models AI Art Style, you can use the provided Colab notebook named "fast-Colab-A1111". Simply open the notebook in a compatible environment, such as A1111 Colab, and follow the instructions to generate images from text descriptions. | |
| ## Acknowledgments | |
| We would like to acknowledge Falah for training the Dreambooth model and TheLastBen for the fast-DreamBooth notebook. | |
| Feel free to explore and experiment with the Models AI Art Style for your text-to-image generation tasks! |