Update README.md

README.md

@@ -12,15 +12,60 @@ tags:
 inference: true
 ---
     
-# DreamBooth - ckandemir/bayc-500
+# DreamBooth - Bored Ape Yacht Club
 
-This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on photo of a bayc nft using [DreamBooth](https://dreambooth.github.io/).
-You can find some example images in the following. 
+## Model Description
 
+This DreamBooth model is an exquisite derivative of `runwayml/stable-diffusion-v1-5`, fine-tuned with an engaging emphasis on the Bored Ape Yacht Club (BAYC) NFT collection. The model's weights were meticulously honed using photos from BAYC NFTs, leveraging the innovative [DreamBooth](https://dreambooth.github.io/) technology to curate a unique, text-to-image synthesis experience. 
+
+
+### Training
+
+Images instrumental in the model's training were generously sourced from the Covalent API, specifically via this [endpoint](https://www.covalenthq.com/docs/api/nft/get-nft-token-ids-for-contract-with-metadata/).
+
+### Inference
+
+Inference has been meticulously optimized, allowing for the generation of captivating, original, and unique images that resonate with the Bored Ape Yacht Club collection. This facilitates a vivid exploration of creativity, enabling the synthesis of images that seamlessly align with the distinctive aesthetics of Bored Ape NFTs.
 
 ![img_0](./image_0.png)
 ![img_1](./image_1.png)
 ![img_2](./image_2.png)
 
 
-DreamBooth for the text encoder was enabled: True.
+## Usage
+
+Here’s a basic example of how you can wield this model for generating images:
+
+```python
+import torch
+from diffusers import StableDiffusionPipeline, DDIMScheduler
+from transformers import CLIPTextModel
+import numpy as np
+
+model_id = "runwayml/stable-diffusion-v1-5"
+
+unet = UNet2DConditionModel.from_pretrained("ckandemir/bayc-diffusion", subfolder="unet")
+text_encoder = CLIPTextModel.from_pretrained("ckandemir/bayc-diffusion",subfolder="text_encoder")
+
+pipeline = StableDiffusionPipeline.from_pretrained(
+    model_id, unet=unet, text_encoder=text_encoder, dtype=torch.float16, use_safetensors=True
+).to('cuda')
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+
+prompt = ["a spiderman bayc nft"]
+neg_prompt = ["realistic,disfigured face,eye patch,disfigured eyes, disfigured, deformed,bad anatomy"] * len(prompt)
+
+# Other parameters like num_samples, guidance_scale, etc., are defined here.
+
+with autocast("cuda"), torch.inference_mode():
+    imgs = pipeline(
+        # Parameters like prompt, negative_prompt, etc., are passed here.
+    ).images
+
+for img in imgs:
+    display(img)
+```
+
+## Optimization
+Results can be further enhanced and refined through meticulous fine-tuning and adept modification of training parameters, unlocking an even broader spectrum of creativity and artistic expression.
+