Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5
| Date | Stars |
|---|---|
| 2026-07-30 | 540 |
| 2026-08-09 | 543 |
| 2026-08-17 | 544 |
| 2026-08-18 | 544 |
| 2026-08-19 | 545 |
| 2026-08-22 | 546 |
| 2026-08-24 | 547 |
| 2026-08-26 | 548 |
| 2026-08-27 | 550 |
| 2026-08-28 | 551 |
| 2026-08-30 | 552 |
| 2026-08-31 | 553 |
| 2026-09-01 | 552 |
| 2026-09-02 | 551 |
| 2026-09-03 | 552 |
| 2026-09-04 | 553 |
| 2026-09-06 | 555 |
| 2026-09-07 | 556 |
| 2026-09-10 | 555 |
| 2026-09-11 | 555 |
| 2026-09-12 | 556 |
| 2026-09-13 | 558 |
| 2026-09-15 | 560 |
| 2026-09-16 | 561 |
| 2026-09-18 | 562 |
| 2026-09-20 | 563 |
| 2026-09-24 | 562 |
| 2026-09-25 | 563 |
| 2026-09-27 | 565 |
| 2026-09-28 | 566 |
| 2026-10-02 | 567 |
| 2026-10-04 | 568 |
| 2026-10-12 | 570 |
| 2026-10-15 | 571 |
| 2026-10-16 | 572 |
| 2026-10-18 | 572 |
| 2026-10-21 | 573 |
| 2026-10-24 | 574 |
| 2026-10-25 | 575 |
| 2026-10-26 | 576 |
| 2026-11-04 | 575 |
Today
-1 stars today
This week
-1 stars this week
This month
+7 stars this month
Momentum
0.0
growth rate 0.00%/day
# ComfyUI Realtime LoRA Toolkit [](https://buymeacoffee.com/lorasandlenses) [](LICENSE) **Train**, **analyze**, **selectively load by block**, and **edit base models** for **SDXL, SD 1.5, FLUX, Z-Image, Qwen Image, Qwen Image Edit, Wan 2.2, and Krea 2 LoRAs** directly inside ComfyUI. One unified interface across three training backends, plus powerful analysis, block-level loading, strength scheduling, and model editing tools. > **Version 2 Now Available:** Combined analyzer + selective loader nodes with strength scheduling and LoRA saving! > > [](https://www.youtube.com/watch?v=3CdyGxvYeHo) ## At a Glance | Backend | Models | Best For | |---------|--------|----------| | **sd-scripts** | SDXL, SD 1.5 | Fast training, mature workflows, broad checkpoint compatibility | | **Musubi Tuner** | Z-Image, Z-Image Base, FLUX Klein 4B/9B, Qwen Image, Qwen Image Edit, Wan 2.2 | Cutting-edge models, smaller LoRAs, excellent VRAM efficiency | | **AI-Toolkit** | FLUX.1-dev, Z-Image, Wan 2.2 alternative training pipeline | **8 training architectures plus Krea 2 LoRA block loading. 3 training backends. 33 nodes total. ** - 10 trainer nodes - 15 selective loaders (6 V1 + 9 V2 combined) - 2 analyzers (V1 + V2) - 6 model layer editors - 1 utility node ## What's New ### FLUX Klein 4B/9B Training & Editing Full training and editing support for Black Forest Labs' fastest FLUX models: **Training** (via Musubi Tuner): - **FLUX Klein 4B** - ~13GB VRAM, Apache 2.0 license - **FLUX Klein 9B** - ~29GB VRAM - **Independent block swap control** - Fine-tune VRAM usage separately from resolution/fp8 settings **Editing & Analysis** (new V2 nodes): - **FLUX Klein 4B Analyzer + Selective Loader V2** - 25 blocks (5 double + 20 single) - **FLUX Klein 9B Analyzer + Selective Loader V2** - 32 blocks (8 double + 24 single) - Per-block strength control, scheduling, and LoRA saving Uses Qwen3 text encoder and FLUX.2 VAE. Train on "base" (undistilled) versions. ### Z-Image Base Training Train with the undistilled Z-Image base model for maximum quality: - Trained LoRAs work with both base and turbo models - Same VRAM presets as turbo trainer (block swaps built into Low/Min modes) - Existing Z-Image V2 Analyzer works with base-trained LoRAs (same architecture) ### V2 Combined Analyzer + Selective Loader Nodes The V2 nodes combine analysis and selective loading into a single node, with powerful new features: - **Strength Scheduling** - Apply LoRA at different strengths during generation using keyframes - **Save Refined LoRA** - Export your block-filtered LoRA as a new file - **40+ Schedule Presets** - Fades, bell curves, pulses, step functions, and inverted versions - **Extra Z-Image Blocks** - Control context_refiner, noise_refiner, final_layer, x_embedder - **Krea 2 LoRA Block Loading** - Control 28 main SingleStreamBlocks, with non-main Krea 2 Linear layers grouped under `other_weights` - **LoKR/LoHa Support** - Proper handling of decomposed LoRA formats (common for Z-Image) ### Model Layer Editor Nodes Scale individual blocks of your **base model** before applying LoRAs: - 6 nodes covering all architectures (SDXL, SD 1.5, FLUX, Z-Image, Wan, Qwen) - Presets for common adjustments - User preset system (save/delete your own configurations) - Save modified models to disk ### Utility Nodes | Node | Description | |------|-------------| | **Scheduled LoRA Loader** | Standalone strength scheduling for any LoRA | See [Utility Nodes](#utility-nodes) section below for full details. ### SDXL Training Improvements - Added `--no_half_vae` option to fix NaN errors with some SDXL checkpoints - Fixed batch_size to 1 for all VRAM presets for stability ### Supported LoRA Formats The analyzer and selective loaders detect and properly handle mult
Excerpt of 29,387 characters
Read on GitHub
133
9
raf
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8cab261c8a90f800, topic:stable-diffusion, topic:comfyui, topic:flux
matched fp:8cab261c8a90f800, topic:lora, name:lora, readme:lora