Update README.md

README.md

@@ -1,3 +1,33 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+pipeline_tag: text-to-image
+library_name: diffusers
+---
+
+![NucleusMoE-Image](demo.png)
+
+NucleusMoE-Image is a 17B flow-based text-to-image generation MoE model with only 2B active parameters. Technical report coming soon...
+
+## Usage
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained("NucleusAI/NucleusMoE-Image", torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+config = TextKVCacheConfig()
+pipe.transformer.enable_cache(config)
+
+prompt = "Vintage-style poster for Artificial Analysis depicting a retro-futuristic cityscape dominated by AI. Towering structures shaped like neural networks loom over sleek flying cars. In the foreground, a stylized robot extends a hand towards the viewer. Bold, sans-serif typography at the top reads 'Welcome to the AI Revolution' with 'Artificial Analysis' prominently displayed at the bottom in a retro chrome effect. The color palette consists of deep blues, vibrant oranges, and metallic silvers, reminiscent of 1950s sci-fi illustrations."
+image = pipe(
+    prompt,
+    height=1024,
+    width=1024,
+    guidance_scale=4.0,
+    num_inference_steps=50,
+).images[0]
+image.save("nucleus_image_demo.png")
+```
+