Swap a large text encoder for a small one with a learned linear projection. MiniMax H3 conditioning from 15.7 GB down to 5.2 GB.
☆183Aug 17, 2026Updated 2 months ago
Alternatives and similar repositories for ComfyUI-ClipProj
Users that are interested in ComfyUI-ClipProj are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ComfyUI custom nodes providing unified image and mask resizing with support for multiple scaling modes, aspect-ratio preservation, center…☆213Sep 21, 2026Updated last month
- Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.☆567Sep 13, 2026Updated last month
- Lightweight FirstBlockCache acceleration node for native ComfyUI MiniMax H3☆113Oct 12, 2026Updated 3 weeks ago
- ☆183Oct 29, 2026Updated last week
- ☆118Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip s…☆714Updated this week
- ☆498Sep 7, 2026Updated last month
- 🚧 Under construction — no-training RefMod reference adapters for MiniMax H3 (compress reference images/videos into tiny latents, no trai…☆611Oct 15, 2026Updated 3 weeks ago
- ☆625Aug 14, 2026Updated 2 months ago
- A model hybridization loader to combine different layers/blocks of the fl2va and ref2va models☆184Aug 11, 2026Updated 2 months ago
- NTSC/VHS analog tape effect for ComfyUI, with a live preview inside the node.☆20Sep 10, 2026Updated last month
- Native ComfyUI nodes for SenseNova U1.5 image generation and multi-reference image editing.☆25Sep 2, 2026Updated 2 months ago
- Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.☆254Oct 7, 2026Updated 3 weeks ago
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆565Oct 14, 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.
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆1,353Oct 18, 2026Updated 2 weeks ago
- Minimax H3 Specific Lora Stack Loader with some additional features.☆18Oct 11, 2026Updated 3 weeks ago
- ComfyUI custom nodes for DLSS 5 Neural Video & Image Enhancer with Frame Interpolation☆141Sep 17, 2026Updated last month
- Prompt editing, ANIMA prompt correction, NAIA prompt integration, LoRA presets, wildcards, model-specific AiO generation for Anima, MOSS …☆36Oct 25, 2026Updated last week
- INT8/INT4 solution for ComfyUI. Compatible with stock loaders and a wide range of models.☆71Oct 28, 2026Updated last week
- ☆146Updated this week
- Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. …☆823Sep 17, 2026Updated last month
- MatlowAI's MiniMax-H3 ComfyUI nodes: Contact-Sheet diffusion + Motion Lab (test-time de-roping of fast motion)☆236Updated this week
- Dual-clock Euler sampler for MiniMax-H3 Turbo LoRA audio-video generation in ComfyUI.☆38Aug 7, 2026Updated 3 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆10Dec 8, 2025Updated 10 months ago
- Official MiniMax-H3 8-step PDD Acc LoRAs (alibaba-pai) in ComfyUI: LoRA + parallel-decoding head bank, euler on trained sigmas, audio+vid…☆136Aug 30, 2026Updated 2 months ago
- Ultimate Model Converter for ComfyUI using comfyui-kitchen - Convert between Transformers, FP32, FP16, FP8. INT8, NVFP4, INT8 Comvrot☆97Updated this week
- HSWQ SD1.5&SDXL&Krea2 ConvRot INT8 Loader, Z Image ConvRot INT8/Hybrid ConvRot NVFP4 Loader and various toos.☆22Oct 25, 2026Updated last week
- Veda Sparse Attention for ComfyUI☆222Oct 11, 2026Updated 3 weeks ago
- FSampler is a training‑free, sampler‑agnostic acceleration layer for diffusion sampling.☆133Feb 28, 2026Updated 8 months ago
- Prompt-free sequential sliding-window MiniMax H3 video outpainting for ComfyUI☆21Sep 8, 2026Updated last month
- Reason-then-encode for Krea 2: the encoder's own Qwen3-VL rewrites your prompt or reads a reference image (describe → filter → combine) b…☆17Jul 8, 2026Updated 3 months ago
- Spectrum for MOSS-Image☆78Oct 24, 2026Updated 2 weeks ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆146Sep 7, 2026Updated last month
- A powerful, ComfyUI Custom node automation suite for generating cinema-production-grade prompts explicitly formatted for the **MiniMax H3…☆262Sep 12, 2026Updated last month
- ☆102Aug 1, 2026Updated 3 months ago
- ☆756Oct 15, 2026Updated 3 weeks ago
- Workflow-compatible NVIDIA RTX Video Super Resolution Pro node for ComfyUI with exact 16K hybrid output, RGB corruption protection, and m…☆44Aug 10, 2026Updated 2 months ago
- Character turnaround and location reference sheets from a MiniMax-H3 camera move, with vision-model frame selection.☆85Aug 14, 2026Updated 2 months ago
- Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which increase speed by up to 1.7x☆254Sep 6, 2026Updated 2 months ago