comfyui_dagthomas

APNextBloom

APNext Bloom Effect Node Creates a bloom effect by making bright areas glow using gaussian blur and blend modes

1 input · 4 parameters · 1 output

APNextColorGrading

APNext Color Grading Effect Node Applies color grading using LUT files or manual controls Supported LUT formats: - .cube files (Adobe/Blackmagic) - .3dl files (Autodesk/Flame) - Image LUTs (.png, .jpg, .tiff, .exr) Example paths: - C:/LUTs/cinematic.cube - ./assets/vintage_film.3dl - /path/to/lut_image.png

1 output

APNextCrossProcessing

APNext Cross Processing Effect Node Simulates cross processing film techniques with channel manipulation and curves

1 input · 12 parameters · 1 output

APNextFilmHalation

APNext Film Halation Effect Node Simulates film halation - light bleeding around bright objects

1 input · 9 parameters · 1 output

APNextGlitchArt

APNext Glitch Art Effect Node Creates digital corruption and glitch effects

1 input · 4 parameters · 1 output

APNextHDRToneMapping

APNext HDR Tone Mapping Effect Node Simulates HDR tone mapping effects for dramatic and surreal looks

1 input · 9 parameters · 1 output

APNextNoise

APNext Noise Effect Node Adds noise to images - can be B&W with transparency or colored based on dominant image colors

1 input · 6 parameters · 1 output

APNextRough

APNext Rough Effect Node Creates a rough, posterized effect by reducing the image to a limited color palette Based on numpy implementation for better performance

1 input · 3 parameters · 1 output

APNextSharpen

APNext Sharpen Effect Node Sharpens images using unsharp mask technique for professional results

1 input · 4 parameters · 1 output

APNextSplitToning

APNext Split Toning Effect Node Applies different colors to highlights and shadows independently

1 input · 7 parameters · 1 output

APNLatent

Compact description unavailable for this node.

0 inputs · 6 parameters · 3 outputs

ClaudeTextNode

Compact description unavailable for this node.

1 output

ClaudeVisionNode

Compact description unavailable for this node.

1 output

CustomPromptLoader

Display Name: APNext Custom Prompts Load prompt templates from the data/customprompts/ directory. Included templates: - promptcreator.txt - Full creative prompt generation - imageanalyze.txt - Image analysis prompts - geminivideo.txt - Video generation prompts - cloner.txt - Style cloning prompts - Various LoRA-specific templates (ohwx, t5xxl, etc.)

1 output

DynamicStringCombinerNode

Compact description unavailable for this node.

0 inputs · 7 parameters · 1 output

FileReaderNode

Compact description unavailable for this node.

0 inputs · 4 parameters · 1 output

FlexibleStringMergerNode

Compact description unavailable for this node.

0 inputs · 4 parameters · 1 output

GeminiCustomVision

Display Name: APNext Gemini Custom Vision Analyze multiple images with custom prompts. Supports dynamic prompt templates with variable substitution. | Input | Description | |-------|-------------| | images | Input images | | customprompt | Custom analysis prompt | | dynamicprompt | Enable ##TAG##, ##SEX##, ##PRONOUNS##, ##WORDS## substitution | | fadepercentage | Blend multiple images together | Returns: (output, clipl, fadedimage)

Dagthomas · 3 outputs

GeminiNextScene

Display Name: APNext Gemini Next Scene Generate cinematic transitions for visual narratives. Creates the "next scene" based on a previous prompt and current frame. | Input | Description | |-------|-------------| | image | Current frame image | | originalprompt | Previous scene description | | focuson | Camera Movement, Framing Evolution, Environmental Reveals, Atmospheric Shifts | | transitionintensity | Subtle, Moderate, or Dramatic | Returns: (nextsceneprompt, shortdescription)

Dagthomas · 2 outputs

GeminiPromptEnhancer

Display Name: APNext Gemini Prompt Enhancer Enhances prompts with cinematic terminology and LLM refinement for video/image generation. | Input | Description | |-------|-------------| | baseprompt | Original prompt to enhance | | enhancementmode | Random Mix, Cinematic/Lighting/Camera/Motion/Style Focus, Full Enhancement, or LLM Only | | usellm | Enable Gemini LLM enhancement | | intensity | Enhancement intensity (0.1-2.0) | | Optional dropdowns | visualstyle, lightingtype, cameraangle, shotsize, lenstype, colortone, etc. | Returns: (enhancedprompt, randomenhanced, llmenhanced)

Dagthomas · 3 outputs

GeminiTextOnly

Display Name: APNext Gemini Text Only Pure text generation with Gemini models. Supports dynamic prompt templates. Returns: (output, clipl)

Dagthomas · 2 outputs

GptCustomVision

Display Name: APNext GPT Custom Vision Full custom vision analysis with GPT-4o.

3 outputs

GptMiniNode

Compact description unavailable for this node.

1 output

GptVisionCloner

Display Name: APNext GPT Vision Cloner Clone image styles using GPT-4o vision capabilities with custom prompts.

3 outputs

GptVisionNode

Compact description unavailable for this node.

1 output

GrokTextNode

Compact description unavailable for this node.

1 output

GrokVisionNode

Compact description unavailable for this node.

1 input · 8 parameters · 1 output

GroqTextNode

Compact description unavailable for this node.

1 output

GroqVisionNode

Compact description unavailable for this node.

1 output

MiniCPMImageNode

Display Name: APNext MiniCPM Image Image understanding with MiniCPM-V 4.5 (OpenBMB). Supports thinking mode for complex reasoning. | Input | Description | |-------|-------------| | images | Input images | | question | Question about the image | | enablethinking | Deep reasoning mode | | precision | bfloat16 or float16 | | unloadafterinference | Free memory after use |

1 input · 8 parameters · 2 outputs

MiniCPMVideoNode

Display Name: APNext MiniCPM Video Video understanding and analysis.

1 input · 14 parameters · 2 outputs

OllamaNode

Display Name: APNext OllamaNode Local LLM inference using Ollama. Supports any model installed in your Ollama instance. | Input | Description | |-------|-------------| | inputtext | Text to process | | modelname | Any Ollama model (llama3, mistral, etc.) | | happytalk, compress | Output controls |

0 inputs · 9 parameters · 1 output

OllamaVisionNode

Compact description unavailable for this node.

Dagthomas · 1 input · 10 parameters · 3 outputs

PGSD3LatentGenerator

Display Name: APNext PGSD3LatentGenerator Optimized latent generation for Stable Diffusion 3 pipelines.

0 inputs · 3 parameters · 1 output

PhiCustomModelInference

Compact description unavailable for this node.

LLM/Phi · 2 inputs · 10 parameters · 3 outputs

PhiModelInference

Compact description unavailable for this node.

LLM/Phi · 2 inputs · 3 parameters · 1 output

PhiModelLoader

Display Name: APNext Phi Model Loader Load Microsoft Phi-3.5-vision-instruct model. | Input | Description | |-------|-------------| | modelversion | Phi-3.5-vision-instruct | | imagecrops | 4 or 16 crops for detail | | attentionmechanism | flashattention2, sdpa, or eager |

LLM/Phi · 0 inputs · 3 parameters · 1 output

PromptGenerator

Compact description unavailable for this node.

0 inputs · 21 parameters · 5 outputs

RandomIntegerNode

Compact description unavailable for this node.

0 inputs · 2 parameters · 1 output

SentenceMixerNode

Compact description unavailable for this node.

0 inputs · 4 parameters · 1 output

StringMergerNode

Compact description unavailable for this node.

2 inputs · 1 parameter · 1 output