Update model card: add zen/zenlm tags, fix branding

README.md

@@ -1,80 +1,64 @@
 ---
-license: mit
-language:
-- en
-pipeline_tag: text-to-image
+language: en
+license: apache-2.0
 tags:
-- diffusers
-- text-to-image
-- image-generation
-- zen
-- zen3
-- zenlm
-- hanzo
+  - zen
+  - zenlm
+  - hanzo
+  - zen3
+  - text-to-image
+  - diffusion
+pipeline_tag: text-to-image
 library_name: diffusers
 ---
 
 # Zen3 Image Dev
 
-**Zen3 Image Dev** is a high-fidelity text-to-image generation model developed by [Hanzo AI](https://hanzo.ai) as part of the Zen model family. It produces photorealistic and artistically detailed images with exceptional prompt adherence.
+Developer variant of Zen3 Image for research and fine-tuning workflows.
 
 ## Overview
 
-Zen3 Image Dev prioritizes image quality and prompt fidelity over speed. It excels at generating detailed, coherent images across a wide range of styles and subjects, making it the premium choice for quality-critical applications.
+Built on **Zen MoDE (Mixture of Distilled Experts)** architecture with 12B parameters.
 
-### Key Features
+Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
 
-- **Exceptional image quality**: State-of-the-art visual fidelity
-- **Strong prompt adherence**: Accurately renders complex descriptions
-- **Versatile style range**: Photorealism, illustration, 3D, and more
-- **High resolution**: Native 1024x1024 with support for other aspect ratios
-
-## Usage
+## Quick Start
 
 ```python
 from diffusers import AutoPipelineForText2Image
 import torch
 
-pipe = AutoPipelineForText2Image.from_pretrained(
-    "zenlm/zen3-image-dev",
-    torch_dtype=torch.bfloat16
-)
-pipe.to("cuda")
-
-image = pipe(
-    "A majestic mountain landscape reflected in a crystal clear alpine lake at golden hour",
-    num_inference_steps=28,
-    guidance_scale=5.0,
-    height=1024,
-    width=1024,
-).images[0]
+model_id = "zenlm/zen3-image-dev"
+pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
 
+image = pipe("A serene mountain landscape at sunset, photorealistic").images[0]
 image.save("output.png")
 ```
 
-## Model Details
-
-| Property | Value |
-|----------|-------|
-| Architecture | Diffusion Transformer |
-| Precision | bfloat16 |
-| License | MIT |
-
 ## API Access
 
-```bash
-curl https://api.hanzo.ai/v1/images/generations \
-  -H "Authorization: Bearer $HANZO_API_KEY" \
-  -H "Content-Type: application/json" \
-  -d '{"model": "zen3-image-dev", "prompt": "A majestic mountain landscape"}'
-```
+```python
+from openai import OpenAI
 
-Get your API key at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.
+client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="your-api-key")
+response = client.images.generate(
+    model="zen3-image-dev",
+    prompt="A serene mountain landscape at sunset",
+    size="1024px",
+)
+print(response.data[0].url)
+```
 
-## License
+## Model Details
 
-MIT
+| Attribute | Value |
+|-----------|-------|
+| Parameters | 12B |
+| Architecture | Zen MoDE |
+| Max Resolution | 1024px |
+| License | Apache 2.0 |
 
----
+## License
 
-*Zen LM is developed by [Hanzo AI](https://hanzo.ai) — Frontier AI infrastructure.*
+Apache 2.0