Categorizer.py was deleted, but __init__.py still listed it, so every
ComfyUI startup printed an import traceback and "Could not load
Categorizer". Also drops it from docs/ai_agents.md and syncs __version__.
Version 2.10.3.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013Lm4YDXhwj49hAA1RKS58Q
Bug fixes:
- FilterImages used imghdr, which was removed in Python 3.13; the import
failure stopped the whole pack from loading. Now uses Pillow, and returns
a newline-joined string instead of a list on a STRING output.
- Dynamic Conditioning / Dynamic Image Switch crashed with no inputs
(unbound variable).
- Dynamic Start Index never advanced because ComfyUI cached its output;
added IS_CHANGED. Same for Load Batch From Dir increment/random modes.
- Dynamic Delay Text always output "" (its timer result went nowhere);
Collect and Distribute Text had the same timer problem.
- People Evaluation Node returned a bare string on errors and printed the
whole prompt to the console.
- Raw latent saver/loader only worked for 1x4x128x128 latents. Now saves
safetensors (same layout as ComfyUI's Save Latent) and still reads old files.
- web/index.js imported the appearance script with the wrong filename case
(breaks on Linux/macOS); the console test script was auto-loaded on every
page load and now lives in tools/.
- Workflow chaining used a hardcoded port 8188, and gives a clear error for
UI-format (non-API) workflow files.
Gemini:
- Shared helper for both Gemini nodes; key config now defaults to the
bundled assets/scripts/api_keys_config.json (paths relative to it), plus
GEMINI_API_KEY env var support.
- "disable" thinking now actually disables it on 2.5 Flash, so thinking no
longer eats max_output_tokens and returns empty text; "enable" uses the
previously unused DEFAULT_THINKING_BUDGET.
- Seed is passed to the API; empty/blocked responses report why.
- Retired 2.0/preview models replaced; custom_model field for new models.
- Audio WAV encoding no longer depends on torchaudio's save backend.
Optimizations:
- Index switches (model/VAE/CLIP/text) use lazy inputs, so only the
selected branch is evaluated.
- __init__ loads modules in a loop and isolates failures per module.
- Prompt nodes share one implementation, read prompt files at run time and
re-run when the file changes (no restart needed).
- LoRA dropdowns use ComfyUI's cached file list and refresh without a
restart; LoRA lookup searches all LoRA folders; hashing uses 1 MB chunks;
DB writes are atomic.
- Load Batch Images concatenates once instead of per image.
- Custom Node Manager parses files instead of executing them.
- requirements.txt drops unused pins (importlib_metadata, packaging,
opencv-python, sounddevice, standard-imghdr).
Version 2.10.0.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013Lm4YDXhwj49hAA1RKS58Q
Added detailed descriptions for various utilities including LoRA DB Builder, LoRA Trigger Lookup, Random/Fixed Audio Picker, System Prompt, and Custom Node Manager.
Expanded documentation for various utilities including Coloring Node, Qwen Aspect Ratio, Save Raw Latent, and Load Latent From Path. Added detailed usage instructions and philosophical context for each utility.
Added detailed descriptions and usage guidelines for various nodes including File Sorter, Media Migrator, Empty Folder Cleaner, Load Batch Images Dir, Load Batch From Dir, Load Video Path, and Sanitize Filename.
Added a section for the Director's Slate AI Cinematographer, detailing its functionality and workflow. Removed descriptions for several other AI tools.
Claude