- Now, nodes can accept Pydantic Schemas as input, making it easier to define structured outputs.
- To generate Pydantic schemas, you can use the Python Interpreter Node by Christian Byrne.
This extension for ComfyUI enables the use of Ollama LLM models, such as Gemma, Llava (multimodal), Llama2, Llama3, and Mistral.
- Ollama Image Describer 🖼️: Generate structured descriptions of images.
- Ollama Text Describer 📝: Extract meaningful insights from text.
- Ollama Image Captioner 📷: Create automatic captions for images.
- Ollama Captioner Extra Options ⚙️: Advanced customization for captions.
- Text Transformer 🔄: Prepend, append, or modify text dynamically.
- JSON Property Extractor 📑: Extract specific values from JSON outputs.
Follow the official Ollama installation guide.
The easiest way to install this extension is through ComfyUI Manager:
- Open ComfyUI Manager.
- Search for ComfyUI-Ollama-Describer.
- Click Install and restart ComfyUI.
git clone https://github.com/alisson-anjos/ComfyUI-Ollama-Describer.gitPath should be custom_nodes\ComfyUI-Ollama-Describer.
Run install.bat
pip install -r requirements.txt
- Extracts structured descriptions from images using vision-enabled LLMs.
- Useful for analyzing images and generating detailed captions, including objects, actions, and surroundings.
model: Select LLaVa models (7B, 13B, etc.).custom_model: Specify a custom model from Ollama's library.api_host: Define the API address (e.g.,http://localhost:11434).timeout: Max response time before canceling the request.temperature: Controls randomness (0 = factual, 1 = creative).top_k,top_p,repeat_penalty: Fine-tune text generation.max_tokens: Maximum response length in tokens.seed_number: Set seed for reproducibility (-1 for random).keep_model_alive: Defines how long the model stays loaded after execution:0: Unloads immediately.-1: Stays loaded indefinitely.- Any other value (e.g.,
10) keeps it in memory for that number of seconds.
prompt: The main instruction for the model.system_context: Provide additional context for better responses.structured_output_format: Accepts either a Python dictionary or a valid JSON string to define the expected response structure.
- Used to extract specific values from structured JSON outputs returned by Ollama Image Describer or Ollama Text Describer.
- Works by selecting a key (or path) inside a JSON structure and outputting only the requested data.
- Useful for filtering, extracting key insights, or formatting responses for further processing.
- Compatible with
structured_output_format, which allows defining structured outputs via a Python dictionary or a valid JSON string.
- Processes text inputs to generate structured descriptions or summaries.
- Ideal for refining text-based outputs and enhancing context understanding.
- Automatically generates concise and relevant captions for images.
- Processes images from a specified folder, iterates through each file, and generates
.txtcaption files saved in the output directory. - Useful for bulk image captioning, dataset preparation, and AI-assisted annotation.
- Useful for image-to-text applications, content tagging, and accessibility.
-
Works in conjunction with Ollama Image Captioner to provide additional customization for captions.
-
Allows fine-tuning of captions by enabling or disabling specific details like lighting, camera angle, composition, and aesthetic quality.
-
Useful for controlling caption verbosity, accuracy, and inclusion of metadata like camera settings or image quality.
-
Helps tailor the output for different applications such as dataset labeling, content creation, and accessibility enhancements.
-
Provides additional customization settings for generated captions.
-
Helps refine style, verbosity, and accuracy based on user preferences.
- Allows users to modify, append, prepend, or replace text dynamically.
- Useful for formatting, restructuring, and enhancing text-based outputs.
| Suffix | Meaning |
|---|---|
| Q | Quantized model (smaller, faster) |
| 4, 8, etc. | Number of bits used (lower = smaller & faster) |
| K | K-means quantization (more efficient) |
| M | Medium-sized model |
| F16 / F32 | Floating-point precision (higher = more accurate) |
More details on quantization: Medium Article.
- Measures how well a model predicts text.
- Lower perplexity = better predictions.
