ComfyUI Node
FunPack Video Refiner V2
Prompt-owned Video Refiner V2. Encodes through the connected CLIP, learns from ratings, and writes LoRA suggestions without sigma/latent/feedback systems.
FunPack Video Refiner V2
- clip
- advisor_clip
- positive_conditioning
- lora_stack
- clip_vision_output
- source_image
- model
- latent
- modified_positive
- status
- training_info
- loss_graph
- encoded_prompts
- model
- video_latent
◄positive_prompt►
◄ratingMissing action►
◄modeRefine►
◄advisor_modeOff►
◄reset_sessionfalse►
◄refinement_key_input►
◄user_intent_prompt►
◄im_feeling_luckyfalse►
◄advisor_thinkingtrue►
◄feedback_prompt►
◄temporal_stylenatural►
◄split_by_transitionsfalse►
◄steer_moderelative►
◄absolute_strength0.60►
CategoryFunPack/Refinement
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| positive_prompt | STRING | — | |
| rating | COMBO | Missing action | 25 options: -Just forget it-, Perfect, Nailed it, Missing details, Missing action, Missing quality, +19 |
| mode | COMBO | Refine | Refine applies learned prompt and conditioning changes. Prompt only shapes the prompt but passes conditioning vectors through unchanged. Learning records observations and ratings while passing everything through unchanged. |
| advisor_mode | COMBO | Off | CLIP text-generation advisor. Full: repair prompt + show diagnostic. Only prompt: repair prompt silently. Only diagnostics: report advice without changing the prompt. Off: disabled. |
| clipopt | CLIP | Optional text encoder. When connected, V2 encodes the prompt itself. | |
| advisor_clipopt | CLIP | Optional separate CLIP/Gemma text generator for Advisor. If disconnected, Advisor falls back to the main CLIP. | |
| positive_conditioningopt | CONDITIONING | Optional pre-encoded Gemma3/LTX2 conditioning. Used only when CLIP is not connected. | |
| reset_sessionopt | BOOLEAN | false | — |
| lora_stackopt | FUNPACK_LORA_STACK | Optional stack from FunPack LoRA Loader. V2 writes prompt-specific suggested weights. | |
| clip_vision_outputopt | CLIP_VISION_OUTPUT | Optional CLIP Vision output describing the source image. Stored as advisory context; it is not blended into positive conditioning. | |
| source_imageopt | IMAGE | Optional original/source image or frame batch. V2 stores size, aspect ratio, and a simple fingerprint to notice changed inputs. | |
| modelopt | MODEL | Optional model. LTX-2 / LTXAV family only - attn2 direction injection, attention temperature, temporal RoPE, and anchor transfer all require LTX transformer internals. Connecting a non-LTX model (e.g. WAN) passes it through unchanged. Connect the model output to your sampler. | |
| refinement_key_inputopt | STRING | Optional linked refinement key, for example from FunPack Refinement Key Loader. Overrides the refinement_key widget when connected. | |
| user_intent_promptopt | STRING | Optional raw user/request prompt. V2 can use this as an intent source to repair missing action/detail/quality phrases if an enhancer omits them. | |
| im_feeling_luckyopt | BOOLEAN | false | Compose a learned prompt from V2 phrase memory, then encode it through the connected CLIP. |
| advisor_thinkingopt | BOOLEAN | true | Let compatible CLIP text generators use thinking mode for advisor diagnostics and prompt repair. |
| feedback_promptopt | STRING | Optional user feedback describing what was specifically wrong with the previous output (e.g. 'he was supposed to hold her hand, not her head'). Has highest priority in the advisor system prompt. | |
| temporal_styleopt | COMBO | natural | Controls how the model perceives motion timing via frame_rate RoPE manipulation. natural=no change, auto=per-scene director picks motion energy from each scene's prompt (needs the Scene Chain Sampler), accelerate=faster motion, decelerate=heavier motion, loop=circular temporal coords, freeze=highly compressed time, pulse=repeated ease-down motion holds per scene (needs the Scene Chain Sampler). |
| split_by_transitionsopt | BOOLEAN | false | Detect transition words and return one conditioning entry per scene for FunPack LTXAV Scene Chain Sampler. Leave off for normal single-conditioning workflows. |
| latentopt | LATENT | Optional video latent for creativity masking. Takes priority over any saved latent for this key. Connect your i2v or previous KSampler output here. | |
| steer_modeopt | COMBO | relative | Relative: per-prompt steering (finds the best conditioning for THIS prompt — default). Absolute: pull conditioning toward the global learned taste, regardless of prompt. Both: layer them. |
| absolute_strengthopt | FLOAT | 0.600–2 | How hard Absolute mode pulls toward the global taste direction. 0.6 is visible but non-destructive; raise for stronger override of the prompt. |
Outputs (7)
| Name | Type | Description |
|---|---|---|
| modified_positive | CONDITIONING | — |
| status | STRING | — |
| training_info | STRING | — |
| loss_graph | IMAGE | — |
| encoded_prompts | STRING | — |
| model | MODEL | — |
| video_latent | LATENT | — |