☆167Oct 6, 2026Updated last month
Alternatives and similar repositories for ai-toolkit-perceptual
Users that are interested in ai-toolkit-perceptual are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.☆79Oct 9, 2026Updated 3 weeks ago
- Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tun…☆681Updated this week
- ☆23Jul 15, 2026Updated 3 months ago
- Optimized ai-toolkit fork without local training data☆25Oct 21, 2026Updated 2 weeks ago
- ☆15Oct 8, 2026Updated 3 weeks ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flux, WAN 2.2, SD 1.5☆575Aug 21, 2026Updated 2 months ago
- Klein edit composite node to mitigate color shift☆154Mar 23, 2026Updated 7 months ago
- MiniMax Fast Batched VAE Decode comfy node☆13Aug 15, 2026Updated 2 months ago
- Caption Creator is a fast and portable tool for generating high-quality image captions and tags - ideal for custom dataset creation. Work…☆34Aug 20, 2026Updated 2 months ago
- Advanced FLUX LoRA manipulation toolkit with GUI interface☆59Nov 5, 2025Updated last year
- ☆26Jun 4, 2026Updated 5 months ago
- This is a vibe coded node for Flux.2 Klein 9b model for adding/altering objects, clothes swapping, face swapping etc.☆15Jun 5, 2026Updated 5 months ago
- Click-to-refine + smart inpaint sampler node for ComfyUI (FLUX 2 Klein). One node: generate, then click / paint / drag to refine, or do l…☆140Aug 8, 2026Updated 2 months ago
- A node created for getting identity consistency for flux.2 klein 9b model.☆16May 31, 2026Updated 5 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆171Sep 16, 2026Updated last month
- A ComfyUI node pack that implements FreeLong (NeurIPS 2024) spectral blending for Wan 2.2 video generation☆168Dec 30, 2025Updated 10 months ago
- [TMLR26]FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time☆249Updated this week
- The node has been created with an objective of identity consistency for FLUX.2 klein 9b models in ComfyUI.☆59May 13, 2026Updated 5 months ago
- Training-free steering dials for MiniMax H3: turn prompt pairs into a 14 KB slider (Freeze <-> Zoomies motion and more)☆39Updated this week
- ComfyUI nodes for local image refinement preprocessing, reference image processing, and paste-back workflows.☆31Aug 6, 2026Updated 3 months ago
- Advanced local tool for intelligent preparation and selection with graphics for training datasets for Loras (Flux/Qwen/Z-image/SDXL/ etc.…☆77Jun 21, 2026Updated 4 months ago
- Faithful ComfyUI implementation of Spectrum for FLUX, using Chebyshev-based spectral feature forecasting to reduce denoiser evaluations.☆13May 16, 2026Updated 5 months ago
- A set of ComfyUI nodes designed specifically for the Z-Image / Z-Image Turbo model.☆367Oct 12, 2026Updated 3 weeks ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- nodes para vfx e low vram do Bernini☆25Aug 18, 2026Updated 2 months ago
- One-click tidy-by-role for ComfyUI workflows. Loaders / encoders / samplers / decoders / outputs each get their own column or row, with o…☆34Jun 7, 2026Updated 4 months ago
- Automated video dataset creator for Windows using WhisperX and Qwen2-VL☆22Jul 30, 2026Updated 3 months ago
- PixlStash helps you find things in an image library that's gotten out of hand. It imports and tags your images automatically, then lets y…☆96Updated this week
- Vision inference with transformers☆10Mar 27, 2025Updated last year
- Ultimate Model Converter for ComfyUI using comfyui-kitchen - Convert between Transformers, FP32, FP16, FP8. INT8, NVFP4, INT8 Comvrot☆97Updated this week
- Free local LoRA training studio: build character, style and concept datasets from one photo or a big image folder, caption them (JoyCapti…☆334Updated this week
- Prompt Rewriter for ComfyUI using llama.cpp for local inference. Supports LLMs, VLMs, and both Instruct and Thinking models.☆21Apr 8, 2026Updated 6 months ago
- MagicNodes, it's a plug-and-play multi-pass "render-machine" for SD/SDXL models. Simple one-node start, expert-grade results. Core is ZeR…☆91May 16, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆183Oct 29, 2026Updated last week
- ComfyUI node that removes the 2px pixel grid left by the Qwen Image, Qwen Image 2.1 and Wan 2.1 VAEs (Krea2, Qwen Image, Anima). Auto-cal…☆97Oct 28, 2026Updated last week
- Advanced triple-stage sampling for Wan2.2 split models with Lightning LoRA - ComfyUI custom node☆107Nov 15, 2025Updated 11 months ago
- Video dataset curation toolkit☆72Feb 24, 2026Updated 8 months ago
- OneTrainer is a one-stop solution for all your Diffusion training needs.☆11Jul 6, 2026Updated 4 months ago
- MirrorMetrics: How to evaluate Stable Diffusion LoRAs. A visual diagnostic tool to detect overfitting, check dataset quality, and fix tra…☆62Feb 21, 2026Updated 8 months ago
- ComfyUI custom node for Flux 2 Klein: image generation, image editing, inpainting, outpainting, faceswap and more. All in a single self-c…☆417Aug 6, 2026Updated 3 months ago