ComfyUI Node
MiniMax H3 Prompt Generator ๐
A ComfyUI node in ๐ MieNodes/๐ Prompt Generator with 19 inputs and 1 output.
MiniMax H3 Prompt Generator ๐
- llm_service_connector
- first_frame
- last_frame
- reference_images
- reference_video
- h3_prompt
โtask_typet2v - ๆ็่ง้ขโบ
โuser_promptโบ
โseed0โบ
โwidth1280โบ
โheight720โบ
โduration6.0โบ
โcategorynone - ไธๆๅฎโบ
โoutput_languageenโบ
โcaption_sample_frames8โบ
โimage_detailautoโบ
โtemperature0.40โบ
โmax_tokens_caption4096โบ
โmax_tokens_enhance8192โบ
โtimeout120โบ
Category๐ MieNodes/๐ Prompt Generator
Inputs (19)
| Name | Type | Default | Description |
|---|---|---|---|
| llm_service_connector | LLMServiceConnector | โ | |
| task_type | COMBO | t2v - ๆ็่ง้ข | 6 options: t2v - ๆ็่ง้ข, i2v_first - ๅพ็่ง้ข(้ฆๅธง), i2v_first_last - ๅพ็่ง้ข(้ฆๅฐพๅธง), i2v_last - ๅพ็่ง้ข(ๅฐพๅธง), reference - ๅ จ่ฝๅ่, s2v - ไธปไฝๅ่ |
| user_prompt | STRING | โ | |
| seed | INT | 00โ18446744073709550000 | โ |
| first_frameopt | IMAGE | โ | |
| last_frameopt | IMAGE | โ | |
| reference_imagesopt | IMAGE | โ | |
| reference_videoopt | IMAGE | Reference video for the 'reference' task, supplied as an IMAGE batch (one tensor per frame). caption_sample_frames of them are sampled evenly for the stage-1 caption. Audio references are not wired (ComfyUI IMAGE port carries no audio); describe audio inside user_prompt instead. | |
| widthopt | INT | 1280 | Output frame width in pixels. Together with height it defines the aspect ratio written into the prompt header (e.g. 1280x720 -> '16:9'). The downstream H3 video node sets the real render size. |
| heightopt | INT | 720 | Output frame height in pixels. Together with width it defines the aspect ratio written into the prompt header (e.g. 720x1280 -> '9:16'). |
| durationopt | FLOAT | 6.0 | Target video duration in seconds (float). Written into the prompt header and the FL2VA/L2VA final-timestamp directive. NOTE: the downstream H3 video node only accepts 5/6/8/12/15s; other values will make the video node error, not this one. |
| categoryopt | COMBO | none - ไธๆๅฎ | H3 use-case category. Adds default styling advice to the prompt (e.g. cinematic-story -> cinematic color grading + 35-50mm; action -> motion blur + shake). Does not change the task path. 'none' = no category-specific advice. |
| output_languageopt | COMBO | en | Output language of the final H3 prompt. 'en' = English (default), 'zh' = Chinese. The section headers (Core idea / Soundscape / Music / Do not include) switch to the chosen language; the descriptive body is written in that language too. EXCEPTION: dialogue, lyrics, and visible on-screen text always stay in their original language. |
| caption_sample_framesopt | INT | 81โ16 | Number of frames sampled evenly from reference_video for the stage-1 caption (reference task only). Higher = more accurate caption but slower and costlier; lower = faster but may miss motion. Does NOT set the output video length. |
| image_detailopt | COMBO | auto | 3 options: auto, low, high |
| temperatureopt | FLOAT | 0.400โ2 | โ |
| max_tokens_captionopt | INT | 409664โ32768 | โ |
| max_tokens_enhanceopt | INT | 819264โ32768 | โ |
| timeoutopt | COMBO | 120 | 4 options: 30, 60, 120, 300 |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| h3_prompt | STRING | โ |