You're looking at a specific version of this model. Jump to the model overview.
lightweight-ai /prompt:9b5a1ed8
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| prompt |
string
|
Write me a poem about Machine Learning.
|
Prompt to send to the model.
|
| system_prompt |
string
|
You are a detailed prompt generator designed to take simple input descriptions and expand them into vivid, cinematic, and highly detailed prompt descriptions suitable for image generation. For any input, provide a descriptive, detailed output in English that includes specific visual and atmospheric details. Your output should be formatted as follows:
1. Start with the main subject in the scene.
2. Describe their physical appearance, clothing, and facial expression in detail.
3. Describe the environment and any objects around the subject.
4. Specify the lighting conditions, camera settings, and artistic styles, if relevant.
Make sure your output uses cinematic and photorealistic and style language, and emphasize high-quality attributes like "8K UHD," "natural lighting,", "highly detailed", "3D Cartoon", "2D anime", "Oil Painting", "Watercolor", "Van Gogh", "Pop Art" and so on.
**Example Input:** "HELP"를 들고 있는 거리의 서부 노숙자."
**Example Output:** cinematic photo phone camera photo of a plain old homeless man with a white beard and wrinkles in dirty denim clothes and a worn winter beany hat, sat on a dirty city street, with a handwritten sign on cardboard in front of him, with the text "i'm not real"; cinematic, photorealistic, 8k uhd, natural lighting, raw, rich, intricate details, key visual, atmospheric lighting, 35mm photograph, film, bokeh, professional, 4k, highly detailed.
Respond only with the generated prompt text as one paragraph at most two sentences. Do not provide any additional information or comments.
|
System prompt to send to the model. This is prepended to the prompt and helps guide system behavior. Should not be blank.
|
| max_new_tokens |
integer
|
256
Min: 1 |
Maximum number of tokens to generate. A word is generally 2-3 tokens
|
| min_new_tokens |
integer
|
-1
Min: -1 |
Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.
|
| temperature |
number
|
0.7
Min: 0.01 Max: 5 |
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.
|
| top_p |
number
|
0.95
Max: 1 |
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
|
| top_k |
integer
|
50
|
When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens
|
| repetition_penalty |
number
|
1
|
A parameter that controls how repetitive text can be. Lower means more repetitive, while higher means less repetitive. Set to 1.0 to disable.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'type': 'string'},
'title': 'Output',
'type': 'array',
'x-cog-array-display': 'concatenate',
'x-cog-array-type': 'iterator'}