Fix attribution: honest base_model + upstream NOTICE; remove false Zen MoDE/scratch claims
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
|
|
|
| 4 |
tags:
|
| 5 |
- image-to-image
|
| 6 |
- zen
|
|
@@ -16,49 +17,36 @@ library_name: diffusers
|
|
| 16 |
|
| 17 |
Instruction-following image editing model for targeted modifications and inpainting.
|
| 18 |
|
|
|
|
|
|
|
| 19 |
## Overview
|
| 20 |
|
| 21 |
-
|
| 22 |
|
| 23 |
-
Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
|
| 24 |
|
| 25 |
## Quick Start
|
| 26 |
|
| 27 |
```python
|
| 28 |
-
from diffusers import
|
| 29 |
import torch
|
| 30 |
|
| 31 |
-
|
| 32 |
-
pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.bfloat16)
|
| 33 |
pipe = pipe.to("cuda")
|
| 34 |
-
|
| 35 |
-
image = pipe("A serene mountain landscape at sunset, photorealistic").images[0]
|
| 36 |
-
image.save("output.png")
|
| 37 |
-
```
|
| 38 |
-
|
| 39 |
-
## API Access
|
| 40 |
-
|
| 41 |
-
```python
|
| 42 |
-
from openai import OpenAI
|
| 43 |
-
|
| 44 |
-
client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="your-api-key")
|
| 45 |
-
response = client.images.generate(
|
| 46 |
-
model="zen-image-edit",
|
| 47 |
-
prompt="A serene mountain landscape at sunset",
|
| 48 |
-
size="1024px",
|
| 49 |
-
)
|
| 50 |
-
print(response.data[0].url)
|
| 51 |
```
|
| 52 |
|
| 53 |
## Model Details
|
| 54 |
|
| 55 |
| Attribute | Value |
|
| 56 |
|-----------|-------|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
| Max Resolution | 1024px |
|
| 60 |
| License | Apache 2.0 |
|
| 61 |
|
| 62 |
-
## License
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
-
Apache 2.0
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen-Image-Edit-2509
|
| 5 |
tags:
|
| 6 |
- image-to-image
|
| 7 |
- zen
|
|
|
|
| 17 |
|
| 18 |
Instruction-following image editing model for targeted modifications and inpainting.
|
| 19 |
|
| 20 |
+
Derived from [Qwen/Qwen-Image-Edit-2509](https://huggingface.co/Qwen/Qwen-Image-Edit-2509) (Apache-2.0); repackaged by Zen.
|
| 21 |
+
|
| 22 |
## Overview
|
| 23 |
|
| 24 |
+
This repository repackages Alibaba's Qwen-Image-Edit-2509 (QwenImageEditPlusPipeline, Qwen2.5-VL text encoder). No weights were trained from scratch by Zen.
|
| 25 |
|
| 26 |
+
Developed/repackaged by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
|
| 27 |
|
| 28 |
## Quick Start
|
| 29 |
|
| 30 |
```python
|
| 31 |
+
from diffusers import QwenImageEditPlusPipeline
|
| 32 |
import torch
|
| 33 |
|
| 34 |
+
pipe = QwenImageEditPlusPipeline.from_pretrained("zenlm/zen-image-edit", torch_dtype=torch.bfloat16)
|
|
|
|
| 35 |
pipe = pipe.to("cuda")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
```
|
| 37 |
|
| 38 |
## Model Details
|
| 39 |
|
| 40 |
| Attribute | Value |
|
| 41 |
|-----------|-------|
|
| 42 |
+
| Base model | Qwen/Qwen-Image-Edit-2509 |
|
| 43 |
+
| Pipeline | QwenImageEditPlusPipeline |
|
|
|
|
| 44 |
| License | Apache 2.0 |
|
| 45 |
|
| 46 |
+
## License & Attribution
|
| 47 |
+
|
| 48 |
+
Apache 2.0. This is a derivative repackaging of [Qwen-Image-Edit-2509](https://huggingface.co/Qwen/Qwen-Image-Edit-2509) by Alibaba (Qwen team), released under the Apache License 2.0. All rights and attribution for the underlying model belong to the original authors.
|
| 49 |
+
|
| 50 |
+
## NOTICE
|
| 51 |
|
| 52 |
+
This product includes the Qwen-Image-Edit-2509 model developed by Alibaba Cloud (Qwen team), licensed under the Apache License 2.0.
|