Update README.md

README.md

@@ -1,6 +1,40 @@
 ---
+tags:
+- image-generation
+- generative-model
+- multimodal
+- SOTA
+model_name: CustomImageGenerator
+model_type: image-generation
+description: >
+  CustomImageGenerator is a state-of-the-art multimodal generative model based
+  on the GPT-2 architecture, capable of generating high-quality images from
+  textual prompts. The model combines advanced techniques from natural language
+  processing (NLP) and computer vision to produce visually coherent and
+  contextually relevant images.
+architecture: GPT-2
+tasks:
+- image-generation
+references:
+- title: Generative Pre-trained Transformer 2.0
+  url: >
+    https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
+- title: Learning to Generate Images from Text
+  url: https://arxiv.org/abs/1511.02793
+- title: Stable Diffusion Models for Image Generation
+  url: https://arxiv.org/abs/2105.05233
+related_models:
+- name: BigGAN
+  description: State-of-the-art generative adversarial network (GAN) for image generation.
+  url: https://github.com/ajbrock/BigGAN-PyTorch
+- name: CLIP
+  description: >
+    Contrastive Language-Image Pre-training model for understanding images and
+    text.
+  url: https://github.com/openai/CLIP
+language:
+- en
 license: apache-2.0
-library_name: diffusers
 ---
 
 <style>