ComfyUI Node
Muse Advanced (GGUF)
A ComfyUI node in VLMPrompt with 29 inputs and 2 outputs.
Muse Advanced (GGUF)
- image
- video
- prompt
- json
◄model_nameGemma4-E4B-uncensored-Q4_K_M►
◄deviceauto►
◄genreRandom►
◄moodRandom►
◄shot_typeRandom►
◄lightingRandom►
◄color_paletteRandom►
◄artistRandom►
◄subjectRandom►
◄eraRandom►
◄free_hint►
◄output_formatJSON + Prompt►
◄aesthetic_biasNone►
◄reference_modeStyle Only►
◄frame_count4►
◄image_max_tokens4096►
◄max_tokens1024►
◄temperature0.85►
◄top_p0.92►
◄repetition_penalty1.10►
◄ctx8192►
◄n_batch512►
◄gpu_layers-1►
◄top_k0►
◄pool_size4194304►
◄keep_model_loadedfalse►
◄seed1►
CategoryVLMPrompt
Inputs (29)
| Name | Type | Default | Description |
|---|---|---|---|
| model_name | COMBO | Gemma4-E4B-uncensored-Q4_K_M | 4 options: Gemma4-E4B-uncensored-Q4_K_M, Qwen3-VL-8B-abliterated-Q4_K_M, Qwen3.5-4B-Uncensored-HauhauCS-Q4_K_M, Qwen3.5-9B-Uncensored-HauhauCS-Q4_K_M |
| device | COMBO | auto | 2 options: auto, cpu |
| genre | COMBO | Random | 79 options: Random, Photo Realism, Cinematic Photography, Street Photography, Landscape Photography, Portrait Photography, +73 |
| mood | COMBO | Random | 50 options: Random, Melancholy, Nostalgia, Loneliness, Quiet Dread, Existential, +44 |
| shot_type | COMBO | Random | 22 options: Random, Wide Establishing Shot, Extreme Wide Shot, Full Shot, Medium Shot, Medium Close-Up, +16 |
| lighting | COMBO | Random | 25 options: Random, Golden Hour, Blue Hour, Midday Harsh Sun, Overcast Soft Light, Candlelight, +19 |
| color_palette | COMBO | Random | 22 options: Random, Desaturated Muted Tones, High Contrast Black & White, Warm Amber & Deep Shadow, Cool Steel Blues, Teal & Orange Cinematic, +16 |
| artist | COMBO | Random | 114 options: Random, None, ── Photographers ──, Gregory Crewdson, Cindy Sherman, Annie Leibovitz, +108 |
| subject | COMBO | Random | 63 options: Random, ── Heroines & Protagonists ──, Heroine — Iconic Hero Pose, Heroine — Battle-Worn Warrior, Heroine — Sci-Fi Captain / Pilot, Heroine — Mech Pilot, +57 |
| era | COMBO | Random | 19 options: Random, Contemporary / Present Day, Near Future (10-30 years), Far Future (centuries ahead), 1980s, 1970s, +13 |
| free_hint | STRING | Optional freeform guidance. Leave empty to dream freely. | |
| output_format | COMBO | JSON + Prompt | 3 options: JSON + Prompt, Prompt Only, JSON Only |
| aesthetic_bias | COMBO | None | 12 options: None, Midjourney v6/v7 — Painterly Realism, Midjourney Niji — Anime/Manga, Stable Diffusion / Tag Style, Photoreal Cinematic, Concept Art / Painterly, +6 |
| reference_mode | COMBO | Style Only | 2 options: Style Only, Style + Subject |
| frame_count | INT | 41–32 | — |
| image_max_tokens | INT | 4096256–1024000 | — |
| max_tokens | INT | 1024256–4096 | — |
| temperature | FLOAT | 0.850–2 | — |
| top_p | FLOAT | 0.920–1 | — |
| repetition_penalty | FLOAT | 1.100.5–2 | — |
| ctx | INT | 81921024–131072 | — |
| n_batch | INT | 51264–32768 | — |
| gpu_layers | INT | -1-1–200 | — |
| top_k | INT | 00–32768 | — |
| pool_size | INT | 41943041048576–10485760 | — |
| keep_model_loaded | BOOLEAN | false | — |
| seed | INT | 11–4294967295 | — |
| imageopt | IMAGE | Optional style reference image | |
| videoopt | IMAGE | Optional video frames as style reference |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | — |
| json | STRING | — |