Maxed-Out-99
2162606f65
Multiple updates across the project: - .gitignore: ignore AGENTS.md - README: refreshed project README with badges, install instructions and node highlights - loraloader_mxd/server/utils_info.py: add structured local LoRA storage (more_info/<model>/lora-info.json) with README creation, legacy .rgthree-info.json fallback, and updated get/delete/save helpers to support LoRA-specific layout while preserving backward compatibility - maxedoutnodes.py: add SmartCropByMaskMXD node (square crop centered on mask), register it in NODE_CLASS_MAPPINGS and display name mappings - wan22nodes.py: add validation and resize helpers (_validate_image_batch_4d, _resize_to_explicit_resolution), FPS resampling (_resample_video_frames_to_fps), WAN22 match-resolution node (WAN22_I2V_Match_Resolution_MXD), expose fps_mode/target_fps in video prep nodes, keep legacy "Safe Auto" behavior while simplifying UI tier options - web/js/betterCombos.js: small UI/identifier changes (rename extension id/name to mxd, add alias for LoadLatent, disable legacy pysssss enhancements behind flag, tweak folder arrow glyphs) - web/mxd_utils_menu.js: replace LoRA chooser with a stylistic tree-style chooser (folder grouping, toggle behavior, styles injection, callback normalization) These changes introduce structured local LoRA metadata handling, new image/video utilities and nodes for WAN 2.2 workflows, and front-end improvements for LoRA choosing and loader UI.
ComfyUI-MaxedOut
Custom ComfyUI nodes built for production workflows, with a focus on SDXL, Flux, and WAN 2.2.
Why This Repo
These are the nodes I use in my own workflows. The goal is speed, cleaner graphs, and fewer repetitive setup steps.
Install
cd ComfyUI\custom_nodes
git clone https://github.com/Maxed-Out-99/ComfyUI-MaxedOut.git
Restart ComfyUI after install.
Featured Nodes
| Node | What it does |
|---|---|
Lora Loader MXD |
Power LoRA loading workflow inspired by rgthree, with practical UX updates and local info tools. |
Image Comparer + Save MXD |
Compare original vs new images in-node and save the new result quickly. |
Video Comparer MXD |
Side-by-side style video comparison flow for before/after checks. |
Flux Empty Latent Image MXD / Flux 2 Empty Latent Image MXD / SDXL Empty Latent Image MXD |
Resolution presets so you do not keep retyping common sizes. |
Save Image MXD |
Simple save modes (Save + Preview, Save Only, Preview Only). |
WAN 2.2 MXD nodes |
Utility nodes for latent/video prep and I2V support in WAN 2.2 workflows. |
Free Workflows
Free workflow releases are posted on Patreon:
- SDXL v1.5 (Free):
[add free Patreon link here] - Mega Flux v1.5 (Free):
[add free Patreon link here] - Patreon profile:
[add Patreon profile link here]
Showcase (Placeholders)
- [Put SDXL v1.5 image here]
- [Put Mega Flux v1.5 image here]
- [Put Image Comparer screenshot here]
- [Put Video Comparer preview GIF/video here]
Notes
Lora Loader MXDis integrated directly in this repo.- Local LoRA info is stored in a structured
more_infoarea to avoid cluttering LoRA folders.
Credits
Lora Loader MXDbuilds on ideas from rgthree Power LoRA Loader.- Media comparer nodes are based on the rgthree comparer concept, with MXD-focused UX adjustments.
Support
If these nodes help your workflow:
- Star this repo.
- Share a result using the nodes.
- Check the free workflows above.