ComfyUI Node
👁️🗨️ NVIDIA Vision Node 👁️🗨️
A ComfyUI node in NVIDIA/Vision with 14 inputs and 1 output.
👁️🗨️ NVIDIA Vision Node 👁️🗨️
- image
- response
◄api_key►
◄modelmeta/llama-3.2-11b-vision-instruct►
◄system_promptYou are a master visual prompt engineer. When given keywords, generate a single, concise, and imaginative AI image prompt. Include only visual details: composition, perspective, depth, lighting, shadows, colours, texture, style, technique, mood, atmosphere, and focal points. Capture the richness and aesthetics a professional artist would consider. Do not include explanations, labels, step-by-step instructions, or extra text. Output only the descriptive prompt itself, in one paragraph, ready for AI image generation. you should write prompt under 300 words.►
◄promptDescribe this image in detail, focusing on its visual elements, artistic style, and overall atmosphere.►
◄max_tokens512►
◄temperature0.70►
◄top_p0.90►
◄frequency_penalty0.0►
◄presence_penalty0.0►
◄streamfalse►
◄use_cachetrue►
◄max_retries3►
◄retry_delay2.0►
CategoryNVIDIA/Vision
Inputs (14)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| model | COMBO | meta/llama-3.2-11b-vision-instruct | 4 options: meta/llama-3.2-11b-vision-instruct, meta/llama-3.2-90b-vision-instruct, meta/llama-3.2-11b-vision, meta/llama-3.2-90b-vision |
| system_prompt | STRING | You are a master visual prompt engineer. When given keywords, generate a single, concise, and imaginative AI image prompt. Include only visual details: composition, perspective, depth, lighting, shadows, colours, texture, style, technique, mood, atmosphere, and focal points. Capture the richness and aesthetics a professional artist would consider. Do not include explanations, labels, step-by-step instructions, or extra text. Output only the descriptive prompt itself, in one paragraph, ready for AI image generation. you should write prompt under 300 words. | — |
| prompt | STRING | Describe this image in detail, focusing on its visual elements, artistic style, and overall atmosphere. | — |
| max_tokens | INT | 51216–4096 | — |
| temperature | FLOAT | 0.700–2 | — |
| top_p | FLOAT | 0.900–1 | — |
| frequency_penalty | FLOAT | 0.0-2–2 | — |
| presence_penalty | FLOAT | 0.0-2–2 | — |
| stream | BOOLEAN | false | — |
| use_cache | BOOLEAN | true | — |
| max_retries | INT | 30–10 | — |
| retry_delay | FLOAT | 2.00.5–30 | — |
| imageopt | IMAGE | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |