> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rendernet.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Generate Media
> The generations endpoint lets users generate media based on various parameters such as aspect ratio, model, prompt etc. The response will return a generation ID for each request, which can be used to track the status and view generated media.
Start using `mode` in character object while generating images using character.
`weight` and `enable_facelock` are deprecated and will be removed in the future.
Example:
```json theme={null}
[
{
.
.
"character": {
"character_id": "char_001",
"mode": "balanced"
}
.
.
}
]
```
Added support for `Video Anyone` generation
Any attempt to produce NSFW, violent, or public figure content will result in permanent account termination.
You can use either a generated image's media\_id or an uploaded image asset's asset\_id as the input image identifier `media_id` for video generation, eliminating the need to re-upload images as assets.
```json Example request theme={null}
[
{
"video_anyone": {
"media_id": "ast_xxxxxxxx",
"prompt": "A person riding a bicycle",
"duration": 5
}
}
]
```
For `video_anyone` generation make sure that input image meets the following conditions to avoid generation failure:
1. Input image aspect ratio should be either `3:5` or `5:3`.
2. Maximum characters permitted for `prompt` is 500 only.
When using the generation array, ensure that each object contains only one of the following properties: `segment`, `style`, `model`, `true_touch`, `narrator` or `video_anyone`. These properties have a priority order as follows:
1. `segment`
2. `style`
3. `model`
4. `true_touch`
5. `narrator`
6. `video_anyone`
If multiple properties are provided, the one with the highest priority will be used.
The `narrator` can be generated either by using a script paired with a voice(List all the available voices using `GET /pub/v1/voices` endpoint) or by utilizing an existing audio asset.
`segment`, `true_touch`, `narrator` and `video_anyone` generations only acknowledge parameters that are passed within their own objects.
For `narrator` generation make sure that video asset meets the following conditions to avoid generation failure:
1. The maximum supported frame rate for a video asset is 30 FPS, calculated by dividing the total number of frames by the total duration.
2. Maximum height and width of the video asset should be `1080` and `1920` respectively.
## OpenAPI
````yaml post /pub/v1/generations
openapi: 3.0.2
info:
description: >-
The Affogato API section provides a comprehensive set of APIs that allow you
to create high-quality media content using textual and graphical inputs. By
utilizing the features provided in this section, users can easily generate
engaging visuals and media assets.You need an API key to use these APIs. To
get your personal key, log in to Affogato, head to the account page at
[Affogato](https://affogato.ai/account) and hit generate API key. Add this
key as an X-API-Key header in the requests that you send.
title: Affogato API
version: '1.0'
servers: []
security: []
tags:
- description: >-
The Generation section allows users to create, view, and delete images on
Rendernet.
name: Generation
- description: >-
Explore all available resources that can be used for generating images on
Rendernet. With this section, users can easily access key details about
the resources at their disposal.
name: Resources
- description: Upload / Get information about assets that can be used for generation.
name: Assets
paths:
/pub/v1/generations:
post:
tags:
- Generation
summary: Generate media
description: >-
The generations endpoint lets users generate media based on various
parameters such as aspect ratio, model, prompt etc. The response will
return a generation ID for each request, which can be used to track the
status and view generated media.
parameters:
- description: >-
API key needed to access our public endpoints. You can find yours
under the 'Account' section of the website
required: true
schema:
type: string
title: X-API-KEY
description: >-
API key needed to access our public endpoints. You can find yours
under the 'Account' section of the website
name: X-API-KEY
in: header
requestBody:
content:
application/json:
schema:
items:
$ref: '#/components/schemas/GenerationRequest'
type: array
responses:
'201':
content:
application/json:
schema:
$ref: '#/components/schemas/GenerationSuccessResponse'
description: A list of submitted generation requests
components:
schemas:
GenerationRequest:
properties:
aspect_ratio:
description: The aspect ratio of the image for the generation
enum:
- '1:1'
- '2:3'
- '3:2'
- '4:5'
- '16:9'
- '9:16'
example: '1:1'
type: string
batch_size:
description: >-
The batch size of the generation (Max permissible value depends on
your subscription plan). Visit [RenderNet
pricing](https://app.rendernet.ai/pricing) for more details
example: 1
type: integer
cfg_scale:
description: >-
AI guidance for this generation. Higher the value, the output will
be closer to the prompt (but may result in distorted images after a
point)
example: 7
maximum: 12
minimum: 4
type: number
character:
$ref: '#/components/schemas/Character'
description: >-
If you want to create images of a character, use the character’s
name in the positive prompt. Example: {character_name} riding a bike
control_net:
$ref: '#/components/schemas/ControlNet'
description: >-
The control net(pose control) for the generation if you want to use
(optional)
facelock:
$ref: '#/components/schemas/Facelock'
description: >-
The face you want to restore for the generation if you want to use
(optional)
loras:
description: >-
Query the list resources endpoint `GET /pub/v1/loras` to view all
available LoRAs. You can add multiple LoRAs to a single generation.
Make sure your LoRAs have the same base model (SD 1.5 / SDXL) as
your selected style/model.
items:
$ref: '#/components/schemas/Lora'
type: array
model:
description: >-
Query the list models endpoint `GET /pub/v1/models` to view all
available models.
example: JuggernautXL
type: string
narrator:
$ref: '#/components/schemas/Narrator'
description: >-
For Narrator generation, pass either `script` or `audio_asset_id`
along with other required details in `narrator` payload.
prompt:
$ref: '#/components/schemas/Prompt'
description: The prompt for the generation
quality:
description: The quality of the image for the generation (Case Sensitive)
enum:
- Plus
- Regular
example: Plus
type: string
sampler:
description: The sampler you want to use for the generation (Case Sensitive)
enum:
- DPM++ 2M Karras
- DPM++ 2M SDE Karras
- DPM++ 2S a Karras
- DPM++ SDE
- DPM++ SDE Karras
- Euler a
example: DPM++ 2M Karras
type: string
seed:
description: >-
The seed for the generation (randomized if you don't want to use a
seed)
example: 1234
type: integer
segment:
$ref: '#/components/schemas/Segment'
description: Changes the input asset image based on the find and replace prompts
steps:
description: The number of steps you want AI to take for the generation
example: 20
maximum: 30
minimum: 10
type: integer
style:
description: >-
Query the list styles endpoint `GET /pub/v1/styles` to view all
available styles.
example: Bokeh
type: string
style_detail:
$ref: '#/components/schemas/StyleDetail'
description: >-
Query the list styles endpoint `GET /pub/v1/styles` to view all
available styles.
true_touch:
$ref: '#/components/schemas/TrueTouch'
description: Enhances and upscales the input image passed in the asset_id
video_anyone:
$ref: '#/components/schemas/VideoAnyone'
description: Convert image to video seamlessly.
type: object
GenerationSuccessResponse:
properties:
data:
$ref: '#/components/schemas/GenerationResponse'
type: object
err:
description: The error if the request was not successful
type: object
type: object
Character:
type: object
properties:
character_id:
description: >-
ID of the character. You can get the details of characters using
`GET /pub/v1/characters` endpoint or else you can create one using
`POST /pub/v1/characters`
example: chr_01
type: string
weight:
description: This parameter is deprecated, use just mode instead
example: 0.6
type: number
minimum: 0.1
maximum: 1
deprecated: true
enable_facelock:
description: This parameter is deprecated, use just mode instead
example: true
type: boolean
deprecated: true
mode:
description: |-
The mode of the character.
- `flexible` - Ideal for stylized characters and image generations.
- `balanced` - Ideal for creating realistic images and more.
- `strong` - Character similarity is most important.
example: balanced
enum:
- flexible
- balanced
- strong
type: string
required:
- character_id
- mode
ControlNet:
type: object
properties:
asset_id:
description: >-
Upload a reference image using the `POST /pub/v1/assets/upload`
endpoint . Pass the asset id in the payload to use the asset as a
reference image for controlnet.
example: ast_01
type: string
control_mode:
description: |
The priority of the control net:
- `0` - The priority between control net and prompt is balanced.
- `1` - The prompt priority is higher than the control net.
- `2` - The control net priority is higher than the prompt.
enum:
- 0
- 1
- 2
example: 0
type: integer
name:
description: >-
Query the list resources endpoint `GET /pub/v1/controlnets` to view
all available controlnets. Make sure your Controlnet has the same
base model (SD 1.5/SDXL) as your selected style/model.
example: Normal
type: string
resize_mode:
description: |-
The relation between the control net image and generated image:
- `0` - Resize and Fill.
- `1` - Crop and Resize.
- `2` - Just Resize.
enum:
- 0
- 1
- 2
example: 0
type: integer
required:
- asset_id
- control_mode
- name
- resize_mode
Facelock:
type: object
properties:
asset_id:
description: >-
Upload a reference image of a person using the `POST
/pub/v1/assets/upload` endpoint. Pass the asset id in the payload to
create AI characters with the same face as the reference image.
example: ast_01
type: string
required:
- asset_id
Lora:
type: object
properties:
name:
description: The name of the lora
example: lora_name
type: string
weight:
description: >-
Specify the strength of the LoRA being applied. Higher values will
influence the generation more.
example: 0.5
maximum: 1
minimum: 0.1
type: number
required:
- name
- weight
Narrator:
type: object
properties:
image_asset_id:
description: >-
ID of an image asset for FaceSwap feature. Upload an image asset
with a face clearly visible, preferably looking forward. You can get
the details of available image assets using `GET
/pub/v2/assets?type=image` endpoint or else you can upload one using
`POST /pub/v2/assets/upload`.
example: ast_imgxxxxx
type: string
video_asset_id:
description: >-
ID of a video asset. Uploaded video asset should have only one
person with a clear view of their face. You can get the details of
available video assets using `GET /pub/v2/assets?type=video`
endpoint or else you can upload one using `POST
/pub/v2/assets/upload?type=video`.
example: ast_vidxxxxx
type: string
audio_asset_id:
description: >-
ID of an audio asset. You can get the details of available audio
assets using `GET /pub/v2/assets?type=audio` endpoint or else you
can upload one using `POST /pub/v2/assets/upload?type=audio`.
example: ast_audxxxxx
type: string
script:
description: Describe/share the script you want to hear in the video narration.
example: Thank you for trying Narrator
type: string
voice:
description: >-
Query the list resources endpoint `GET /pub/v1/voices` to view all
available voices, and use any one from it for narrator generation.
example: Rachel
type: string
required:
- video_asset_id
Prompt:
type: object
properties:
negative:
description: The negative prompt
example: >-
nsfw, deformed, extra limbs, bad anatomy, deformed pupils, text,
worst quality, jpeg artifacts, ugly, duplicate, morbid, mutilated
type: string
positive:
description: >-
The positive prompt. If you are submitting a character for
generation then make sure to pass the character's name in curly
braces here. For ex. {Alex} on a trek
example: a man looking into the camera
type: string
required:
- negative
- positive
Segment:
type: object
properties:
asset_id:
description: >-
Upload an image using the upload asset endpoint `POST
/pub/v1/assets/upload`
example: ast_01
type: string
find:
description: >-
Describe an element in the image that you want to change. Specify
only 1 element at a time (eg: black tshirt, red car, hair, etc).
example: red shirt
type: string
replace:
description: >-
Describe the element you want to see in the image instead (eg: a
yellow tshirt, a white car, pink hair, etc).
example: blue shirt
type: string
required:
- asset_id
- find
- replace
StyleDetail:
properties:
name:
description: The name of the style
example: Black & White
type: string
base_model:
description: The base model of the style
type: string
example: flux
TrueTouch:
type: object
properties:
asset_id:
description: >-
Upload an image using the upload asset endpoint `POST
/pub/v1/assets/upload`
example: ast_01
type: string
enhance_strength:
description: >-
Specify the level of realistic enhancement you want to apply to your
image.
example: 0.5
type: number
scale_factor:
description: Specify how much you want to upscale the your image by.
enum:
- '1'
- '1.5'
- '2'
- '2.5'
- '3'
example: 1.5
type: number
required:
- asset_id
- enhance_strength
- scale_factor
VideoAnyone:
type: object
properties:
media_id:
description: >-
This can be either generated image's media_id or an uploaded image
asset's asset_id that you want to convert to video. (Supported
Aspect Ratio: `3:5` or `5:3`)
example: ast_01
type: string
prompt:
description: >-
A simple prompt to be described that what subject wants to be done
in the video. (The video prompt is not mandatory input for
generating video. You can choose to skip it, and we will create a
video based on the source image)
example: Camera static, a woman riding a bicycle
type: string
duration:
description: Duration of the output video in seconds
enum:
- 5
- 10
example: 5
type: number
default: 5
required:
- media_id
GenerationResponse:
properties:
credits_remaining:
description: The number of credits remaining
example: 20
type: integer
generation_id:
description: The id of the generation
example: gen_01
type: string
media:
items:
$ref: '#/components/schemas/ImageMetadata'
type: array
result:
description: The result status of the generation
example: initiated
type: string
type: object
ImageMetadata:
properties:
id:
description: The id of the media
example: model_01
type: string
dim:
$ref: '#/components/schemas/ImageSize'
model:
description: >-
The model used for the media if model is used in the generation else
it won't be present
example: JuggernautXL
type: string
status:
description: The status of the image
example: initiated
type: string
style:
description: >-
The style used for the media if style is used in the generation else
it won't be present
example: Bokeh
type: string
style_detail:
$ref: '#/components/schemas/StyleDetail'
description: >-
The style name along with its base model used for the generation.
This will only be present in case of a style generation.
type:
description: The type of the media generation.
example: image
type: string
type: object
ImageSize:
type: object
properties:
height:
description: The height of the image
example: 512
type: integer
width:
description: The width of the image
example: 512
type: integer
required:
- height
- width
````