Update model card: Remove emojis, fix usage example, remove zoo-gym tag, add diffusers/zenlm tags, remove fake benchmarks

README.md

@@ -3,81 +3,83 @@ license: apache-2.0
 base_model: zenlm/zen-image-edit
 tags:
 - image-editing
+- image-to-image
+- text-to-image
 - vision
 - multimodal
+- diffusers
 - zen
-- zoo-gym
-- hanzo-ai
-- text-to-image
-- image-to-image
+- zenlm
+- hanzo
 language:
 - en
 - zh
 pipeline_tag: image-to-image
-library_name: transformers
+library_name: diffusers
 ---
 
-# Zen-Image-Edit 🎨
-
-Part of the [Zen AI Model Family](https://huggingface.co/zenlm/zen-family) | Based on Zen Image Edit
+# Zen Image Edit
 
-## ✨ Model Highlights
+**Zen LM by Hanzo AI** — Advanced image editing model with natural language instructions. Edit images by describing changes in plain text.
 
-Advanced 7B image editing model with natural language instructions:
-- **Object Manipulation**: Add, remove, move objects seamlessly
-- **Style Transfer**: Apply artistic styles and filters
-- **Background Editing**: Replace or modify backgrounds
-- **Face Editing**: Adjust expressions and features
-- **Resolution**: Up to 1024x1024
-- **Speed**: 3-5 images/second on A100
+## Overview
 
-## 📊 Performance
+Zen Image Edit enables precise image editing through natural language instructions:
+- Object manipulation: Add, remove, or move objects seamlessly
+- Style transfer: Apply artistic styles and filters
+- Background editing: Replace or modify backgrounds
+- Facial editing: Adjust expressions and features
+- Resolution: Up to 1024x1024
 
-| Benchmark | Score |
-|-----------|-------|
-| EditBench | 87.3% |
-| MagicBrush | 82.1% |
-| InstructPix2Pix | 89.5% |
-| ImageNet-E | 91.2% |
-
-## 💻 Quick Start
+## Usage
 
 ```python
-from transformers import AutoModelForImageEditing, AutoProcessor
+from diffusers import AutoPipelineForInpainting
 from PIL import Image
+import torch
 
-model = AutoModelForImageEditing.from_pretrained("zenlm/zen-image-edit")
-processor = AutoProcessor.from_pretrained("zenlm/zen-image-edit")
+pipe = AutoPipelineForInpainting.from_pretrained(
+    "zenlm/zen-image-edit",
+    torch_dtype=torch.bfloat16,
+    trust_remote_code=True,
+)
+pipe = pipe.to("cuda")
 
 image = Image.open("input.jpg")
-instruction = "Remove the car and add trees"
-
-inputs = processor(images=image, text=instruction, return_tensors="pt")
-edited_image = model.generate(**inputs)
-edited_image.save("output.jpg")
+edited = pipe(
+    image=image,
+    prompt="Remove the car and replace with trees",
+    height=1024,
+    width=1024,
+).images[0]
+edited.save("output.jpg")
 ```
 
-## 🎨 Editing Capabilities
+## API Access
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url='https://api.hanzo.ai/v1',
+    api_key='your-api-key',
+)
+
+response = client.images.edit(
+    model='zen-image-edit',
+    image=open('input.jpg', 'rb'),
+    prompt='Remove the car and replace with trees',
+    size='1024x1024',
+)
+print(response.data[0].url)
+```
 
-- **Object Removal**: Clean inpainting with context awareness
-- **Object Addition**: Natural placement with proper lighting
-- **Style Transfer**: Artistic transformations
-- **Color Grading**: Professional color adjustments
-- **Background Swap**: Seamless background replacement
-- **Face Editing**: Expression and feature modification
-- **Weather Effects**: Add rain, snow, fog
-- **Time of Day**: Convert day to night scenes
+Get your API key at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.
 
-## 📦 Available Formats
+## License
 
-| Format | Size | Use Case |
-|--------|------|----------|
-| SafeTensors | 14GB | Full precision |
-| GGUF Q8 | 7GB | High quality |
-| GGUF Q4 | 3.5GB | Mobile/edge |
-| MLX 8-bit | 7GB | Apple Silicon |
-| MLX 4-bit | 3.5GB | iOS devices |
+Apache 2.0
 
 ---
 
-Built by Hanzo AI × Zoo Labs Foundation
+*Zen LM is developed by [Hanzo AI](https://hanzo.ai) — Frontier AI infrastructure.*