ComfyUI_VLM_nodes

ChatMusician

Compact description unavailable for this node.

CreativeArtPromptGenerator

Compact description unavailable for this node.

Joytag

Compact description unavailable for this node.

VLM Nodes/JoyTag · 1 output

JsonToText

Compact description unavailable for this node.

VLM Nodes/Text · 1 input · 0 parameters · 1 output

KeywordExtraction

Compact description unavailable for this node.

Kosmos2model

Compact description unavailable for this node.

VLM Nodes/Kosmos 2 · 1 input · 1 parameter · 1 output

LLava Loader Simple

Compact description unavailable for this node.

VLM Nodes/LLava · 1 input · 4 parameters · 1 output

LlavaClipLoader

Compact description unavailable for this node.

VLM Nodes/LLava · 0 inputs · 1 parameter · 1 output

LLavaOptionalMemoryFreeAdvanced

Compact description unavailable for this node.

VLM Nodes/LLava · 2 inputs · 15 parameters · 1 output

LLavaOptionalMemoryFreeSimple

Compact description unavailable for this node.

VLM Nodes/LLava · 2 inputs · 7 parameters · 1 output

LLavaPromptGenerator

Compact description unavailable for this node.

LLavaSamplerAdvanced

Compact description unavailable for this node.

LLavaSamplerSimple

Compact description unavailable for this node.

LLMLoader

Compact description unavailable for this node.

VLM Nodes/LLM · 0 inputs · 4 parameters · 1 output

LLMOptionalMemoryFreeAdvanced

Compact description unavailable for this node.

VLM Nodes/LLM · 1 input · 14 parameters · 1 output

LLMOptionalMemoryFreeSimple

Compact description unavailable for this node.

VLM Nodes/LLM · 1 input · 6 parameters · 1 output

LLMPromptGenerator

Compact description unavailable for this node.

LLMSampler

Compact description unavailable for this node.

MCLLaVAModel

Compact description unavailable for this node.

VLM Nodes/MC LLaVA · 1 input · 5 parameters · 1 output

MiniCPMNode

Compact description unavailable for this node.

VLM Nodes/MiniCPM V · 1 input · 7 parameters · 1 output

MolmoNode

Compact description unavailable for this node.

VLM Nodes/Molmo · 1 input · 8 parameters · 1 output

MoonDream

Compact description unavailable for this node.

VLM Nodes/MoonDream · 1 input · 1 parameter · 1 output

Moondream2model

Compact description unavailable for this node.

VLM Nodes/Moondream2 · 1 input · 1 parameter · 1 output

Paligemma

Compact description unavailable for this node.

VLM Nodes/Paligemma · 3 outputs

PlayMusic

Compact description unavailable for this node.

VLM Nodes/Audio · 2 inputs · 2 parameters

PromptGenerateAPI

Compact description unavailable for this node.

VLM Nodes/LLM · 0 inputs · 7 parameters · 1 output

Qwen2VLNode

Utilizes the latest Qwen2-VL series of models, which are state-of-the-art vision language models supporting various resolutions, ratios, and languages. The models excel at: - Understanding images of various resolutions & ratios - Complex visual reasoning and decision making - Multilingual support (English, Chinese, European languages, Japanese, Korean, Arabic, Vietnamese, etc.) Available models include 2B, 7B, and 72B parameter versions, with standard, AWQ, and GPTQ quantized variants. It will automatically download the necessary files into models/LLavacheckpoints/filesforqwen2vl. Important Note: Larger models (7B, 72B) require significant VRAM. Choose quantized versions (AWQ, GPTQ) for reduced memory usage.

VLM Nodes/Qwen2 VL · 2 inputs · 7 parameters · 1 output

SaveAudioNode

Compact description unavailable for this node.

VLM Nodes/Audio · 0 outputs

SimpleText

Compact description unavailable for this node.

VLM Nodes/Text · 0 inputs · 1 parameter · 1 output

StructuredOutput

Getting structured outputs can be quite challenging through prompt engineering alone. I've added the Structured Output node to VLM Nodes. Now, you can obtain your answers reliably. You can extract entities, numbers, classify prompts with given classes, and generate one specific prompt. These are just a few examples. You can add additional descriptions to fields and choose the attributes you want it to return.

VLM Nodes/LLM · 2 inputs · 5 parameters · 1 output

Suggester

Compact description unavailable for this node.

UformGen2QwenNode

UForm-Gen2 is an extremely fast small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. It will automatically download the necessary files into models/LLavacheckpoints/filesforuformgen2qwen

VLM Nodes/UformGen2Qwen · 1 input · 1 parameter · 1 output

ViewText

Compact description unavailable for this node.

VLM Nodes/Text · 1 input · 0 parameters · 1 output