ComfyUI Node
Generate Text Advanced BETA (Venice)
Text Generation node that makes use of Venice.AI's text generation API. Use Textgen Parameters (Venice) node to pass on extra Venice.AI specific parameters.Does not have chat history context.
Generate Text Advanced BETA (Venice)
- image_for_vision
- response
◄modelllama-3.1-405b►
◄prompt►
◄system_prompt►
◄enable_system_prompttrue►
◄frequency_penalty0.00►
◄presence_penalty0.00►
◄repetition_penalty1.20►
◄max_temp1.50►
◄min_temp0.10►
◄max_completion_tokens420►
◄temperature0.50►
◄top_k40►
◄top_p0.80►
◄min_p0.05►
◄enable_visionfalse►
◄venice_parameters—►
Categoryvenice.ai
Inputs (17)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | llama-3.1-405b | The model to use for text generation. |
| prompt | STRING | The prompt to generate text from. Ask, command or chat with the model. | |
| system_prompt | STRING | Optional system prompt to guide the model's behavior. | |
| enable_system_prompt | BOOLEAN | true | Enable or disable system prompt being passed on. |
| frequency_penalty | FLOAT | 0.00-2–2 | Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. |
| presence_penalty | FLOAT | 0.00-2–2 | Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. |
| repetition_penalty | FLOAT | 1.200–2 | 1.0 means no penalty. Values > 1.0 discourage repetition. |
| max_temp | FLOAT | 1.500–2 | Maximum temperature value for dynamic temperature scaling. |
| min_temp | FLOAT | 0.100–2 | Minimum temperature value for dynamic temperature scaling. |
| max_completion_tokens | INT | 4201–131072 | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. |
| temperature | FLOAT | 0.500–2 | Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. |
| top_k | INT | 40 | The number of highest probability vocabulary tokens to keep for top-k-filtering. |
| top_p | FLOAT | 0.800–2 | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. |
| min_p | FLOAT | 0.050–1 | Sets a minimum probability threshold for token selection. Tokens with probabilities below this value are filtered out. |
| enable_vision | BOOLEAN | false | Enable or disable vision tasks. Requires image_for_vision input to be populated and for the LLM to actually support vision tasks to process. |
| venice_parametersopt | STRING | Optional input. Use the Textgen Parameters (Venice) node to use extra, venice specific parameters for text generation. | |
| image_for_visionopt | IMAGE | Optional input. Add an image for vision-supported LLMs to process. Will only be processed if 'enable_vision' is 'True' and if the LLM actually supports vision tasks. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |