ComfyUI Node
FunPack Story Writer
A ComfyUI node in FunPack with 24 inputs and 5 outputs.
FunPack Story Writer
- prompt1
- prompt2
- prompt3
- prompt4
- prompt5
◄user_promptA photo of a [subject] in a [setting]. [action].►
◄prompt1►
◄prompt2►
◄prompt3►
◄prompt4►
◄prompt5►
◄story_system_prompt►
◄sequence_system_prompt►
◄model_path_type▾►
◄model_pathmlabonne/NeuralLlama-3-8B-Instruct-abliterated►
◄llm_safetensors_file▾►
◄prompt_count3►
◄top_p0.75►
◄top_k40►
◄min_p0.10►
◄temperature0.60►
◄max_new_tokens512►
◄repetition_penalty1.00►
◄mode▾►
◄vision_inputPut outputs of your VL model here to make the Story Writer aware of the starting image.►
◄sanity_checktrue►
◄sanity_check_system_promptAnalyze the given sequence and perform a correction, if the sequence does not match the given requirements:
1. The sequence is related to given user's prompt.
2. The sequence contains only physically possible actions.
3. The sequence contains information about characters, their appearances, positioning, actions, camera angle, focus and zoom.
4. The sequence is fully describing the requested action.
Output ONLY corrected sequence, or return it unchanged if it matches the requirements. No additional text except for sequence is allowed.►
◄disable_continuityfalse►
◄provide_current_idtrue►
CategoryFunPack
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| user_prompt | STRING | A photo of a [subject] in a [setting]. [action]. | — |
| prompt1 | STRING | — | |
| prompt2 | STRING | — | |
| prompt3 | STRING | — | |
| prompt4 | STRING | — | |
| prompt5 | STRING | — | |
| story_system_prompt | STRING | — | |
| sequence_system_prompt | STRING | — | |
| model_path_type | COMBO | 2 options: Local Safetensors, HuggingFace Pretrained | |
| model_path | STRING | mlabonne/NeuralLlama-3-8B-Instruct-abliterated | — |
| llm_safetensors_file | COMBO | 0 options: | |
| prompt_count | INT | 31–5 | — |
| top_p | FLOAT | 0.750–2 | — |
| top_k | INT | 400–1000 | — |
| min_p | FLOAT | 0.100–1 | — |
| temperature | FLOAT | 0.600–2 | — |
| max_new_tokens | INT | 51264–4096 | — |
| repetition_penalty | FLOAT | 1.000–3 | — |
| mode | COMBO | 2 options: Sequences from story, Sequences from user prompt | |
| vision_input | STRING | Put outputs of your VL model here to make the Story Writer aware of the starting image. | — |
| sanity_check | BOOLEAN | true | — |
| sanity_check_system_prompt | STRING | Analyze the given sequence and perform a correction, if the sequence does not match the given requirements: 1. The sequence is related to given user's prompt. 2. The sequence contains only physically possible actions. 3. The sequence contains information about characters, their appearances, positioning, actions, camera angle, focus and zoom. 4. The sequence is fully describing the requested action. Output ONLY corrected sequence, or return it unchanged if it matches the requirements. No additional text except for sequence is allowed. | — |
| disable_continuity | BOOLEAN | false | — |
| provide_current_id | BOOLEAN | true | — |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| prompt1 | STRING | — |
| prompt2 | STRING | — |
| prompt3 | STRING | — |
| prompt4 | STRING | — |
| prompt5 | STRING | — |