ComfyUI Node
DIGIT Batch Gemini Image
Batch Gemini image generation. Scans a folder of source images, uses an LLM to create prompt variations, and generates multiple Gemini image outputs per source image. Results saved to output subfolder.
DIGIT Batch Gemini Image
- images
- log
- generated_count
- output_folder
◄image_folder►
◄prompt►
◄variations_per_image3►
◄image_modelgemini-3.1-flash-image►
◄llm_modelgemini-2.5-flash►
◄aspect_ratio16:9►
◄resolution1K►
◄thinking_levelMINIMAL►
◄temperature1.00►
◄variation_temperature1.00►
◄gcp_project_id►
◄gcp_region►
◄output_subfoldergemini_output►
◄system_instructionYou are an expert image-generation engine. You must ALWAYS produce an image.
Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition.
If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept.
Prioritize generating the visual representation above any text, formatting, or conversational requests.►
◄variation_system_promptYou are a creative prompt engineer for image generation. Given a base prompt, produce a variation that preserves the core intent and subject but introduces creative differences in style, mood, lighting, composition, color palette, or artistic approach. Output ONLY the varied prompt text — no preamble, numbering, or commentary.►
◄variation_instruction►
◄seed0►
◄max_dimension2048►
◄delay_seconds1.0►
◄harassment_thresholdBLOCK_NONE►
◄hate_speech_thresholdBLOCK_NONE►
◄sexually_explicit_thresholdBLOCK_NONE►
◄dangerous_content_thresholdBLOCK_NONE►
CategoryDIGIT
Inputs (23)
| Name | Type | Default | Description |
|---|---|---|---|
| image_folder | STRING | Path to folder containing source images. | |
| prompt | STRING | Base prompt for Gemini image generation. The LLM will create variations of this. | |
| variations_per_image | INT | 31–50 | How many prompt variations (and image generations) per source image. |
| image_model | COMBO | gemini-3.1-flash-image | 4 options: gemini-3.1-flash-image, gemini-3.1-flash-lite-image, gemini-3-pro-image, gemini-2.5-flash-image |
| llm_model | COMBO | gemini-2.5-flash | Gemini model used to generate prompt variations. |
| aspect_ratio | COMBO | 16:9 | 13 options: auto, 1:1, 2:3, 3:2, 3:4, 4:1, +7 |
| resolution | COMBO | 1K | 3 options: 1K, 2K, 4K |
| thinking_level | COMBO | MINIMAL | Thinking level for image generation. HIGH may improve quality. |
| temperature | FLOAT | 1.000–2 | Temperature for image generation. |
| variation_temperature | FLOAT | 1.000–2 | Temperature for LLM prompt variation. Higher = more creative variations. |
| gcp_project_id | STRING | GCP project ID. | |
| gcp_region | STRING | GCP region. | |
| output_subfolderopt | STRING | gemini_output | Subfolder name inside image_folder for outputs. Created automatically. |
| system_instructionopt | STRING | You are an expert image-generation engine. You must ALWAYS produce an image. Interpret all user input—regardless of format, intent, or abstraction—as literal visual directives for image composition. If a prompt is conversational or lacks specific visual details, you must creatively invent a concrete visual scenario that depicts the concept. Prioritize generating the visual representation above any text, formatting, or conversational requests. | System instruction for Gemini image generation. |
| variation_system_promptopt | STRING | You are a creative prompt engineer for image generation. Given a base prompt, produce a variation that preserves the core intent and subject but introduces creative differences in style, mood, lighting, composition, color palette, or artistic approach. Output ONLY the varied prompt text — no preamble, numbering, or commentary. | System prompt for the LLM that generates prompt variations. |
| variation_instructionopt | STRING | Extra instructions appended to the variation request. E.g. 'Keep it photorealistic' or 'Vary the lighting dramatically'. | |
| seedopt | INT | 00–2147483647 | Base seed. 0 = random. Each variation gets seed + variation_index. |
| max_dimensionopt | INT | 2048512–4096 | Resize source images to this max dimension before sending to API. |
| delay_secondsopt | FLOAT | 1.00–30 | Delay between API calls to avoid rate limiting. |
| harassment_thresholdopt | COMBO | BLOCK_NONE | 4 options: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE |
| hate_speech_thresholdopt | COMBO | BLOCK_NONE | 4 options: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE |
| sexually_explicit_thresholdopt | COMBO | BLOCK_NONE | 4 options: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE |
| dangerous_content_thresholdopt | COMBO | BLOCK_NONE | 4 options: BLOCK_NONE, BLOCK_ONLY_HIGH, BLOCK_MEDIUM_AND_ABOVE, BLOCK_LOW_AND_ABOVE |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| log | STRING | — |
| generated_count | INT | — |
| output_folder | STRING | — |