Create README.md

README.md

@@ -0,0 +1,41 @@
+
+fine-tuned with text-image dataset `friedrichor/PhotoChat_120_square_HQ`
+
+# Model Details
+
+- Model type: Diffusion-based text-to-image generation model
+- Language(s): English
+- fine-tuning dataset: [friedrichor/PhotoChat_120_square_HQ](https://huggingface.co/datasets/friedrichor/PhotoChat_120_square_HQ)
+
+## Dataset
+[friedrichor/PhotoChat_120_square_HQ](https://huggingface.co/datasets/friedrichor/PhotoChat_120_square_HQ) was used for fine-tuning Stable Diffusion v2.1.  
+
+120 image-text pairs  
+
+Images were manually screened from the [PhotoChat](https://aclanthology.org/2021.acl-long.479/) dataset, cropped to square, and `Gigapixel` was used to improve the quality.   
+Image captions are generated by [BLIP-2](https://arxiv.org/abs/2301.12597).
+
+# Simple use example
+
+```python
+import torch
+from diffusers import StableDiffusionPipeline
+
+device = "cuda:0"
+pipe = StableDiffusionPipeline.from_pretrained("friedrichor/stable-diffusion-v2.1-portraiture", torch_dtype=torch.float32)
+pipe.to(device)
+
+prompt = "a woman in a red and gold costume with feathers on her head"
+extra_prompt = ", facing the camera, photograph, highly detailed face, depth of field, moody light, style by Yasmin Albatoul, Harry Fayt, centered, extremely detailed, Nikon D850, award winning photography"
+negative_prompt = "cartoon, anime, ugly, (aged, white beard, black skin, wrinkle:1.1), (bad proportions, unnatural feature, incongruous feature:1.4), (blurry, un-sharp, fuzzy, un-detailed skin:1.2), (facial contortion, poorly drawn face, deformed iris, deformed pupils:1.3), (mutated hands and fingers:1.5), disconnected hands, disconnected limbs"
+
+generator = torch.Generator(device=device).manual_seed(42)
+image = pipe(prompt + extra_prompt,
+             negative_prompt=negative_prompt,
+             height=768, width=768,
+             num_inference_steps=20,
+             guidance_scale=7.5,
+             generator=generator).images[0]
+image.save("image.png")
+```
+