GITBOOK-592: docs: add hints and separate example for z-image lora

Author: techpro-aimlapi

docs/.gitbook/assets/j-z8clom9AqL_2ZTsGygk.png

@@ -291,6 +291,8 @@
     * [v5/text-to-video](api-references/video-models/pixverse/v5-text-to-video.md)
     * [v5/image-to-video](api-references/video-models/pixverse/v5-image-to-video.md)
     * [v5/transition](api-references/video-models/pixverse/v5-transition.md)
+    * [v5.5/text-to-video](api-references/video-models/pixverse/v5-5-text-to-video.md)
+    * [v5.5/image-to-video](api-references/video-models/pixverse/v5-5-image-to-video.md)
   * [Runway](api-references/video-models/runway/README.md)
     * [gen3a\_turbo](api-references/video-models/runway/gen3a_turbo.md)
     * [gen4\_turbo](api-references/video-models/runway/gen4_turbo.md)

docs/.gitbook/assets/yYDEEEN5bzcsn-6MeiHHM.png

@@ -16,7 +16,8 @@ This documentation is valid for the following list of our models:
 
 ## Model Overview
 
-An ultra-fast 6B-parameter text-to-image model with LoRA[^1] support.
+An ultra-fast 6B-parameter text-to-image model with LoRA[^1] support \
+(see [a separate example](z-image-turbo-lora.md#example-2-text-to-image-with-lora-fine-tuning) of how to use it).
 
 ## Setup your API Key
 
@@ -28,7 +29,7 @@ If you don’t have an API key for the AI/ML API yet, feel free to use our [Quic
 [OpenAPI z-image-turbo-lora](https://raw.githubusercontent.com/aimlapi/api-docs/refs/heads/main/docs/api-references/image-models/Alibaba-Cloud/z-image-turbo-lora.json)
 {% endopenapi-operation %}
 
-## Quick Example
+## Example #1: Standard Text-to-Image
 
 Let's generate an image of the specified size using a simple prompt.
 
@@ -53,7 +54,7 @@ def main():
             "image_size": {
                 "width": 1440,
                 "height": 512
-            },
+            }
         }
     )
 
@@ -124,4 +125,148 @@ We obtained the following 1440x512 image by running this code example:
 
 <figure><img src="../../../.gitbook/assets/-IaUBYEQiYqRaeT7oZvus.png" alt=""><figcaption></figcaption></figure>
 
+***
+
+## Example #2: Text-to-Image with LoRA Fine-Tuning
+
+The `alibaba/z-image-turbo-lora` model supports applying up to three LoRA adapters to modify the style or behavior of the base model.
+
+The `loras` parameter is an **array of objects**, not strings. Each object describes a single LoRA:
+
+* `path` — where to load the LoRA from (Hugging Face repo ID, direct URL to the weights file, or local path).
+* `scale` — how strongly this LoRA should influence the result (typically between `0.6` and `1.0`).
+
+<details>
+
+<summary>Community LoRAs on Hugging Face that are compatible with Z-Image Turbo</summary>
+
+**Style LoRAs**
+
+* `renderartist/Classic-Painting-Z-Image-Turbo-LoRA` – classic oil painting / “old masters” look, museum-like style.
+* `renderartist/Coloring-Book-Z-Image-Turbo-LoRA` – “coloring book” style with clear outlines and flat fills, good for children’s illustrations and icons.
+* `ostris/z_image_turbo_childrens_drawings` — a stylish LoRA adaptation for generating artistic children's drawings.&#x20;
+* `renderartist/Technically-Color-Z-Image-Turbo` – vivid, cinematic Technicolor-style colors and dramatic lighting.
+* `suayptalha/Z-Image-Turbo-Realism-LoRA` – boosts photorealism; includes the trigger word `Realism`.
+* `AlekseyCalvin/HistoricColor_Z-image-Turbo-LoRA` – historical early-1900s color photography inspired by three-color processes.
+* `MGRI/Z-Image-Turbo-Panyue-Lora` – character LoRA for the digital persona **Panyue** (triggers: `Panyue`, `潘悦`).
+
+**Technical / utility LoRAs**
+
+* `GuangyuanSD/Z-Image-Re-Turbo-LoRA` – Re-Turbo adapter that restores Turbo-level speed while behaving like a de-turbo model for training and advanced workflows.
+* `ostris/zimage_turbo_training_adapter` – training adapter / de-distill LoRA used as a base for building new LoRAs on top of Z-Image Turbo.
+
+</details>
+
+***
+
+Let's generate an image using a LoRA to influence the visual style.
+
+{% tabs %}
+{% tab title="Python" %}
+{% code overflow="wrap" %}
+```python
+import requests
+import json  # for getting a structured output with indentation
+
+def main():
+    response = requests.post(
+        "https://api.aimlapi.com/v1/images/generations",
+        headers={
+            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
+            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
+            "Content-Type": "application/json",
+        },
+        json={
+            "model": "alibaba/z-image-turbo-lora",
+            "prompt": "A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.",
+            "image_size": {
+                "width": 1440,
+                "height": 512
+            },
+            "loras":[
+                {
+                  "path": "ostris/z_image_turbo_childrens_drawings",
+                  "scale": 0.85
+                }
+            ]
+        }
+    )
+
+    data = response.json()
+    print(json.dumps(data, indent=2, ensure_ascii=False))
+
+if __name__ == "__main__":
+    main()
+```
+{% endcode %}
+{% endtab %}
+
+{% tab title="JS" %}
+{% code overflow="wrap" %}
+```javascript
+async function main() {
+  const response = await fetch('https://api.aimlapi.com/v1/images/generations', {
+    method: 'POST',
+    headers: {
+      // Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
+      'Authorization': 'Bearer <YOUR_AIMLAPI_KEY>',
+      'Content-Type': 'application/json',
+    },
+    body: JSON.stringify({
+      model: 'alibaba/z-image-turbo-lora',
+      prompt: 'A T-Rex relaxing on a beach, lying on a sun lounger and wearing sunglasses.',
+      image_size: {
+        width: 1440,
+        height: 512
+      },
+      loras:[
+        {
+          path: 'ostris/z_image_turbo_childrens_drawings',
+          scale: 0.85
+        }
+      ]
+    }),
+  });
+
+  const data = await response.json();
+  console.log('Generation:', data);
+}
+
+main();
+```
+{% endcode %}
+{% endtab %}
+{% endtabs %}
+
+<details>
+
+<summary>Response</summary>
+
+{% code overflow="wrap" %}
+```json5
+{
+  "data": [
+    {
+      "url": "https://cdn.aimlapi.com/flamingo/files/b/0a85ed1b/j-z8clom9AqL_2ZTsGygk.png"
+    }
+  ],
+  "meta": {
+    "usage": {
+      "credits_used": 17850
+    }
+  }
+}
+```
+{% endcode %}
+
+</details>
+
+We obtained the following 1440x512 image by running this code example:
+
+<figure><img src="../../../.gitbook/assets/j-z8clom9AqL_2ZTsGygk.png" alt=""><figcaption></figcaption></figure>
+
+The scale parameter significantly affects the output. The previous example was generated with `scale` = `0.85`, and here’s what happens when we increase it to `1.0`:
+
+<figure><img src="../../../.gitbook/assets/yYDEEEN5bzcsn-6MeiHHM.png" alt=""><figcaption></figcaption></figure>
+
 [^1]: The **LoRA algorithm** (Low-Rank Adaptation) is a parameter-efficient fine-tuning technique used to adapt large language models (LLMs) and stable diffusion models to new tasks or domains without retraining the entire model. This process is faster and requires significantly less memory and computational resources than full fine-tuning.

docs/SUMMARY.md

@@ -6,15 +6,15 @@ noIndex: true
 # Hunyuan Part
 
 {% columns %}
-{% column width="66.66666666666666%" %}
+{% column %}
 {% hint style="info" %}
 This documentation is valid for the following list of our models:
 
 * `tencent/hunyuan-part`
 {% endhint %}
 {% endcolumn %}
 
-{% column width="33.33333333333334%" %}
+{% column %}
 <a href="https://aimlapi.com/app/hunyuan/hunyuan-image-v3-text-to-image" class="button primary">Try in Playground</a>
 {% endcolumn %}
 {% endcolumns %}

docs/api-references/image-models/alibaba-cloud/z-image-turbo-lora.md

@@ -1,7 +1,7 @@
 # qwen-max
 
 {% columns %}
-{% column %}
+{% column width="66.66666666666666%" %}
 {% hint style="info" %}
 This documentation is valid for the following list of our models:
 
@@ -10,7 +10,7 @@ This documentation is valid for the following list of our models:
 {% endhint %}
 {% endcolumn %}
 
-{% column %}
+{% column width="33.33333333333334%" %}
 <a href="https://aimlapi.com/app/alibaba/qwen-max" class="button primary">Try in Playground</a>
 {% endcolumn %}
 {% endcolumns %}
@@ -25,25 +25,25 @@ The large-scale Mixture-of-Experts (MoE) language model. Excels in language unde
 
 <summary>Step-by-Step Instructions</summary>
 
-#### :digit\_one: Setup You Can’t Skip
+:digit\_one: **Setup You Can’t Skip**
 
 :black\_small\_square: [**Create an Account**](https://aimlapi.com/app/sign-up): Visit the AI/ML API website and create an account (if you don’t have one yet).\
 :black\_small\_square: [**Generate an API Key**](https://aimlapi.com/app/keys): After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.
 
-#### :digit\_two: Copy the code example
+:digit\_two: **Copy the code example**
 
 At the bottom of this page, you'll find [a code example](qwen-max.md#code-example) that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.
 
-#### :digit\_three: Modify the code example
+:digit\_three: **Modify the code example**
 
 :black\_small\_square: Replace `<YOUR_AIMLAPI_KEY>` with your actual AI/ML API key from your account.\
 :black\_small\_square: Insert your question or request into the `content` field—this is what the model will respond to.
 
-#### :digit\_four: <sup><sub><mark style="background-color:yellow;">(Optional)<mark style="background-color:yellow;"><sub></sup> Adjust other optional parameters if needed
+:digit\_four: <sup><sub><mark style="background-color:yellow;">**(Optional)**<mark style="background-color:yellow;"><sub></sup>**&#x20;Adjust other optional parameters if needed**
 
 Only `model` and `messages` are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding [API schema](qwen-max.md#api-schema), which lists all available parameters along with notes on how to use them.
 
-#### :digit\_five: Run your modified code
+:digit\_five: **Run your modified code**
 
 Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.
 

docs/api-references/image-models/tencent/hunyuan-part.md

@@ -1,15 +1,15 @@
 # qwen-turbo
 
 {% columns %}
-{% column %}
+{% column width="66.66666666666666%" %}
 {% hint style="info" %}
 This documentation is valid for the following list of our models:
 
 * `qwen-turbo`
 {% endhint %}
 {% endcolumn %}
 
-{% column %}
+{% column width="33.33333333333334%" %}
 <a href="https://aimlapi.com/app/alibaba/qwen-turbo" class="button primary">Try in Playground</a>
 {% endcolumn %}
 {% endcolumns %}
@@ -25,25 +25,25 @@ Large context window (<kbd>1,000,000</kbd> tokens).
 
 <summary>Step-by-Step Instructions</summary>
 
-#### :digit\_one: Setup You Can’t Skip
+:digit\_one: **Setup You Can’t Skip**
 
 :black\_small\_square: [**Create an Account**](https://aimlapi.com/app/sign-up): Visit the AI/ML API website and create an account (if you don’t have one yet).\
 :black\_small\_square: [**Generate an API Key**](https://aimlapi.com/app/keys): After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.
 
-#### :digit\_two: Copy the code example
+:digit\_two: **Copy the code example**
 
 Below, you'll find [a code example](qwen-turbo.md#code-example) that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.
 
-#### :digit\_three: Modify the code example
+:digit\_three: **Modify the code example**
 
 :black\_small\_square: Replace `<YOUR_AIMLAPI_KEY>` with your actual AI/ML API key from your account.\
 :black\_small\_square: Insert your question or request into the `content` field—this is what the model will respond to.
 
-#### :digit\_four: <sup><sub><mark style="background-color:yellow;">(Optional)<mark style="background-color:yellow;"><sub></sup> Adjust other optional parameters if needed
+:digit\_four: <sup><sub><mark style="background-color:yellow;">**(Optional)**<mark style="background-color:yellow;"><sub></sup>**&#x20;Adjust other optional parameters if needed**
 
 Only `model` and `messages` are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding [API schema](qwen-turbo.md#api-schema), which lists all available parameters along with notes on how to use them.
 
-#### :digit\_five: Run your modified code
+:digit\_five: **Run your modified code**
 
 Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.
 

docs/api-references/text-models-llm/Alibaba-Cloud/qwen-max.md

@@ -1,7 +1,7 @@
 # Claude 3 Haiku
 
 {% columns %}
-{% column %}
+{% column width="66.66666666666666%" %}
 {% hint style="info" %}
 This documentation is valid for the following list of our models:
 
@@ -12,7 +12,7 @@ This documentation is valid for the following list of our models:
 {% endhint %}
 {% endcolumn %}
 
-{% column %}
+{% column width="33.33333333333334%" %}
 <a href="https://aimlapi.com/app/claude-3-haiku-20240307" class="button primary">Try in Playground</a>
 {% endcolumn %}
 {% endcolumns %}

docs/api-references/text-models-llm/Alibaba-Cloud/qwen-turbo.md

@@ -1,15 +1,15 @@
 # Qwen3-235B-A22B
 
 {% columns %}
-{% column %}
+{% column width="66.66666666666666%" %}
 {% hint style="info" %}
 This documentation is valid for the following model:
 
 * `Qwen/Qwen3-235B-A22B-fp8-tput`
 {% endhint %}
 {% endcolumn %}
 
-{% column %}
+{% column width="33.33333333333334%" %}
 <a href="https://aimlapi.com/app/qwen/qwen3-235b-a22b-fp8-tput" class="button primary">Try in Playground</a>
 {% endcolumn %}
 {% endcolumns %}
@@ -24,25 +24,25 @@ A hybrid instruct-and-reasoning text model.
 
 <summary>Step-by-Step Instructions</summary>
 
-#### :digit\_one: Setup You Can’t Skip
+:digit\_one: **Setup You Can’t Skip**
 
 :black\_small\_square: [**Create an Account**](https://aimlapi.com/app/sign-up): Visit the AI/ML API website and create an account (if you don’t have one yet).\
 :black\_small\_square: [**Generate an API Key**](https://aimlapi.com/app/keys): After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.
 
-#### :digit\_two: Copy the code example
+:digit\_two: **Copy the code example**
 
 At the bottom of this page, you'll find [a code example](qwen3-235b-a22b.md#code-example) that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.
 
-#### :digit\_three: Modify the code example
+:digit\_three: **Modify the code example**
 
 :black\_small\_square: Replace `<YOUR_AIMLAPI_KEY>` with your actual AI/ML API key from your account.\
 :black\_small\_square: Insert your question or request into the `content` field—this is what the model will respond to.
 
-#### :digit\_four: <sup><sub><mark style="background-color:yellow;">(Optional)<mark style="background-color:yellow;"><sub></sup> Adjust other optional parameters if needed
+:digit\_four: <sup><sub><mark style="background-color:yellow;">**(Optional)**<mark style="background-color:yellow;"><sub></sup>**&#x20;Adjust other optional parameters if needed**
 
 Only `model` and `messages` are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding [API schema](qwen3-235b-a22b.md#api-schema), which lists all available parameters along with notes on how to use them.
 
-#### :digit\_five: Run your modified code
+:digit\_five: **Run your modified code**
 
 Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.
 

docs/api-references/text-models-llm/Anthropic/claude-3-haiku.md

@@ -39,8 +39,8 @@ Below, you can find both corresponding API schemas.
 
 ### Create a video generation task and send it to the server
 
-{% hint style="warning" %}
-The ratio/aspect\_ratio parameter is deprecated. The aspect ratio of the generated video is solely determined by the aspect ratio of the input reference image.
+{% hint style="info" %}
+The aspect ratio of the generated video is solely determined by the aspect ratio of the input reference image.
 {% endhint %}
 
 {% openapi src="../../../.gitbook/assets/v1-pro-image-to-video.json" path="/v2/generate/video/kling/generation" method="post" %}