NVIDIA Sol-Attn for ComfyUI / Triton kernel on SM89 - SM121, with zero-copy MiniMax H3 nodes: memory-efficient attention, scheduled tau with graph preview, and feed-forward chunking. Measured 1.14–1.44× vs SageAttention and −37% MLP peak VRAM on H3
☆159Aug 13, 2026Updated 2 months ago
Alternatives and similar repositories for ComfyUI-sol-attn
Users that are interested in ComfyUI-sol-attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆498Sep 7, 2026Updated last month
- Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip s…☆714Updated this week
- ☆265Sep 15, 2026Updated last month
- Sol-attn comfy plug-in just for Blackwell☆74Aug 4, 2026Updated 3 months ago
- ComfyUI custom nodes providing unified image and mask resizing with support for multiple scaling modes, aspect-ratio preservation, center…☆213Sep 21, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆625Aug 14, 2026Updated 2 months ago
- Ultimate H3: one MiniMax H3 workflow for ComfyUI in four windows (Setup, Director, Seeds, Output). 1-4 full seeds with sound to pick from…☆36Updated this week
- Native MiniMax-H3 inference acceleration for ComfyUI, integrating Exact Runtime optimizations with Sana Sol-Attn, rectangular Q/KV attent…☆53Updated this week
- ComfyUI custom node for Ideogram 4 Magic Prompt and Ideogram 4 aspect-ratio resolution selection. FREE PROMPT API☆13Jun 4, 2026Updated 5 months ago
- 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
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆565Oct 14, 2026Updated 3 weeks ago
- Upscale long, high-resolution MiniMax H3 video on a VRAM-limited GPU in a single node.☆254Oct 7, 2026Updated 3 weeks ago
- Semantic Conditioning Bridge for MiniMax H3☆41Sep 14, 2026Updated last month
- Timestep-cache acceleration for MiniMax H3 in ComfyUI — open source, cross-platform, ~3x speedup measured☆19Aug 4, 2026Updated 3 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- 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
- Script that automates Cracking Sora invitation codes by Brute force☆20Oct 1, 2025Updated last year
- ComfyUI nodes for MOSS-TTS-Local-Transformer-v1.5 , a 48 kHz stereo local Transformer TTS model with direct generation, zero-shot voice c…☆31Jun 28, 2026Updated 4 months ago
- Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins☆1,353Oct 18, 2026Updated 2 weeks ago
- ComfyUI custom nodes for LongCat-AudioDiT \ Diffusion-based Zero-Shot Text-to-Speech☆142Apr 4, 2026Updated 7 months ago
- A better cache node for MiniMax H3 / 专为 MiniMax H3 优化的缓存加速节点☆77Aug 3, 2026Updated 3 months ago
- ☆406Sep 18, 2026Updated last month
- FireRedTTS3 for ComfyUI: multilingual zero-shot voice cloning, voice design, speech editing, Whisper transcripts, AIMDO DynamicVRAM, with…☆23Aug 18, 2026Updated 2 months ago
- MiniMaxH3_LatentUpscaler for ComfyUI☆281Aug 17, 2026Updated 2 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.
- Minimax video audio Concat AV Latent for any video into Minimax H3 sampler☆72Aug 6, 2026Updated 3 months ago
- Video Delta Net hybrid attention for MiniMax-H3 as a native ComfyUI node.☆27Oct 21, 2026Updated 2 weeks ago
- Veda Sparse Attention for ComfyUI☆222Oct 11, 2026Updated 3 weeks 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
- Experimental test to freeze video latents while continuing with audio processing, to increase audio quality in low-step turbo MiniMax H3 …☆163Sep 8, 2026Updated last month
- MatlowAI's MiniMax-H3 ComfyUI nodes: Contact-Sheet diffusion + Motion Lab (test-time de-roping of fast motion)☆236Updated this week
- ComfyUI custom nodes for Zyphra/ZONOS2, with text-to-speech, audio-only voice cloning, SDPA and FlashAttention inference, and ComfyUI/AI…☆13Jun 14, 2026Updated 4 months ago
- Video Delta Net hybrid attention for MiniMax-H3 as a native ComfyUI node.☆244Sep 12, 2026Updated last month
- Windows / Linux desktop app built with Rust/Tauri for local Higgs Audio v3 TTS inference + local dev api through a native C++/CUDA port☆36Jul 15, 2026Updated 3 months 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.
- Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. …☆34Oct 8, 2026Updated 3 weeks ago
- ☆26Sep 8, 2026Updated last month
- Create algorithmic artwork through various procedural generation algorithms.☆12Apr 7, 2025Updated last year
- Lightweight FirstBlockCache acceleration node for native ComfyUI MiniMax H3☆113Oct 12, 2026Updated 3 weeks ago
- ☆1,262Updated this week
- ☆756Oct 15, 2026Updated 3 weeks ago
- ☆146Sep 7, 2026Updated last month