zeekay commited on
Commit
f93bac7
·
verified ·
1 Parent(s): 22ce91e

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

Browse files
Files changed (1) hide show
  1. README.md +36 -37
README.md CHANGED
@@ -1,66 +1,65 @@
1
  ---
2
- library_name: diffusers
3
- pipeline_tag: text-to-image
4
  tags:
5
- - diffusers
6
- - text-to-image
7
- - image-generation
8
- - japanese
9
  - zen
10
- - zen3
11
  - zenlm
12
  - hanzo
13
- license: apache-2.0
 
 
 
 
 
14
  ---
15
 
16
- # Zen3 Image JP
17
 
18
- **Zen LM by Hanzo AI** — Japanese-optimized image generation with enhanced Japanese text rendering and aesthetics.
19
 
20
- ## Specs
21
 
22
- | Property | Value |
23
- |----------|-------|
24
- | Parameters | 12B |
25
- | Resolution | 1024x1024 |
26
- | Architecture | Zen MoDE (Mixture of Distilled Experts) |
27
- | Generation | Zen3 |
28
 
29
- ## Usage
30
 
31
  ```python
32
  from diffusers import AutoPipelineForText2Image
33
  import torch
34
 
35
- pipe = AutoPipelineForText2Image.from_pretrained(
36
- "zenlm/zen3-image-jp",
37
- torch_dtype=torch.float16,
38
- )
39
  pipe = pipe.to("cuda")
40
 
41
- image = pipe(
42
- "A serene Japanese garden with cherry blossoms",
43
- num_inference_steps=50,
44
- guidance_scale=5.0,
45
- ).images[0]
46
  image.save("output.png")
47
  ```
48
 
49
  ## API Access
50
 
51
- ```bash
52
- curl https://api.hanzo.ai/v1/images/generations \
53
- -H "Authorization: Bearer $HANZO_API_KEY" \
54
- -H "Content-Type: application/json" \
55
- -d '{"model": "zen3-image-jp", "prompt": "A serene Japanese garden with cherry blossoms"}'
 
 
 
 
 
56
  ```
57
 
58
- Get your API key at [console.hanzo.ai](https://console.hanzo.ai) — $5 free credit on signup.
 
 
 
 
 
 
 
59
 
60
  ## License
61
 
62
  Apache 2.0
63
-
64
- ---
65
-
66
- *Zen LM is developed by [Hanzo AI](https://hanzo.ai) — Frontier AI infrastructure.*
 
1
  ---
2
+ language: en
3
+ license: apache-2.0
4
  tags:
 
 
 
 
5
  - zen
 
6
  - zenlm
7
  - hanzo
8
+ - zen3
9
+ - text-to-image
10
+ - diffusion
11
+ - japanese
12
+ pipeline_tag: text-to-image
13
+ library_name: diffusers
14
  ---
15
 
16
+ # Zen3 Image Jp
17
 
18
+ Japanese-optimized variant of Zen3 Image for localized text-to-image generation.
19
 
20
+ ## Overview
21
 
22
+ Built on **Zen MoDE (Mixture of Distilled Experts)** architecture with 12B parameters.
23
+
24
+ Developed by [Hanzo AI](https://hanzo.ai) and the [Zoo Labs Foundation](https://zoo.ngo).
 
 
 
25
 
26
+ ## Quick Start
27
 
28
  ```python
29
  from diffusers import AutoPipelineForText2Image
30
  import torch
31
 
32
+ model_id = "zenlm/zen3-image-jp"
33
+ pipe = AutoPipelineForText2Image.from_pretrained(model_id, torch_dtype=torch.bfloat16)
 
 
34
  pipe = pipe.to("cuda")
35
 
36
+ image = pipe("A serene mountain landscape at sunset, photorealistic").images[0]
 
 
 
 
37
  image.save("output.png")
38
  ```
39
 
40
  ## API Access
41
 
42
+ ```python
43
+ from openai import OpenAI
44
+
45
+ client = OpenAI(base_url="https://api.hanzo.ai/v1", api_key="your-api-key")
46
+ response = client.images.generate(
47
+ model="zen3-image-jp",
48
+ prompt="A serene mountain landscape at sunset",
49
+ size="1024px",
50
+ )
51
+ print(response.data[0].url)
52
  ```
53
 
54
+ ## Model Details
55
+
56
+ | Attribute | Value |
57
+ |-----------|-------|
58
+ | Parameters | 12B |
59
+ | Architecture | Zen MoDE |
60
+ | Max Resolution | 1024px |
61
+ | License | Apache 2.0 |
62
 
63
  ## License
64
 
65
  Apache 2.0