H3-Tiny: structured pruning of MiniMax H3 Ref2VA (33B → 17B → 14B)
☆24Nov 20, 2026Updated this week
Alternatives and similar repositories for H3-Tiny
Users that are interested in H3-Tiny are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Add-on nodes for ComfyUI-H3-FaceRefine (MiniMax H3): anti-wobble Flow Lock, Stitch Plus, Tone Match, strength presets and method B workfl…☆34Updated this week
- Universal LoRA Training for ComfyUI - Zero External Dependencies, Any Model, Any GPU.☆47Updated this week
- Analog film-inspired photographic finishing for ComfyUI, featuring 50 film emulsions, adjustable Emulsion Response, optical effects, film…☆29Updated this week
- VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation☆32Nov 4, 2026Updated 2 weeks ago
- ggml inference code for ZONOS2☆14Nov 13, 2026Updated last week
- 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.
- Fit, stylize, transfer, and camera-drive native SAM3D Body MHR pose data in ComfyUI.☆32Jul 29, 2026Updated 3 months ago
- Practical MiniMax-H3 prompt validation, canvas planning, audio reroll, and AV latent tools for ComfyUI.☆11Nov 11, 2026Updated last week
- ComfyUI nodes, workflow, and converted LoRA for Open-H3-Regenerate-2K-IC☆55Nov 9, 2026Updated last week
- Render it ten ways, keep the one you love. An open-weights film studio for MiniMax H3 in ComfyUI: takes, lineage, cast and an agent skill…☆43Oct 30, 2026Updated 3 weeks ago
- Native Qt desktop app for building MiniMax H3 reference packages with ComfyUI☆10Oct 8, 2026Updated last month
- Inference-time Diff-Aid-inspired text-conditioning patches for ComfyUI: sparse Flux/WAN block modulation and an SDXL cross-attention vari…☆18Nov 13, 2026Updated last week
- Learning Representations to Guide Pixel Diffusion Transformers☆16Oct 18, 2026Updated last month
- ☆27Nov 9, 2026Updated last week
- ComfyUI nodes for LongCat-Video-Avatar 1.6 by PixelAI Labs: one photo + a voice = a lip-synced talking avatar video. Official INT8, 8 ste…☆12Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- WeMM-Video is a family of omni-modal foundation models by WeChat Vision at Tencent, excelling in omni-modal video understanding and reaso…☆51Updated this week
- Prompt-free sequential sliding-window MiniMax H3 video outpainting for ComfyUI☆22Sep 8, 2026Updated 2 months ago
- ☆64Oct 24, 2026Updated 3 weeks ago
- Upscale a finished MiniMax H3 clip in ComfyUI: H3 latent upscaler + one guided re-draw in tiles, with the h3upscale x2 LoRA (on Hugging F…☆51Updated this week
- Relive and celebrate your life's milestones on a personal, interactive timeline. A nostalgic journey through your history with anniversar…☆12Apr 16, 2024Updated 2 years ago
- ☆13Oct 11, 2026Updated last month
- Local AuK Base and AuK-Flash speech generation, voice cloning, editing, enhancement and separation. Uses ComfyUI model management, attent…☆48Sep 18, 2026Updated 2 months ago
- ☆54Updated this week
- ComfyUI nodes for SAM3DBody and SAM3.1 multi-person OpenPose estimation☆31Nov 7, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆20Updated this week
- Director flow for ComfyUI, custom node that enalbes generation of long videos without OOM by using the last frame of each generation as i…☆32Aug 18, 2026Updated 3 months ago
- VoxMel: Wavelet-Factorized Autoregressive Mel-Spectrogram Modeling for Zero-Shot Speech Synthesis☆201Updated this week
- Cleaner MiniMax-H3-Image text-to-image in ComfyUI: Steering and a Re-Noise Sampler against grainy fine texture, and a Resolution Selector…☆45Updated this week
- ComfyUI Timeline Studio for MiniMax H3: multi-shot video, visual memory across scenes and angles, and local or cloud Story writing.☆197Updated this week
- Experimental test to freeze video latents while continuing with audio processing, to increase audio quality in low-step turbo MiniMax H3 …☆174Sep 8, 2026Updated 2 months ago
- ☆10Mar 5, 2026Updated 8 months ago
- ☆189Updated this week
- ComfyUI custom nodes for LavaSR — a fast speech enhancement and audio super-resolution model that upsamples degraded audio to 48 kHz with…☆12Feb 27, 2026Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A ComfyUI extension that integrates Meta’s Sapiens2 models for high-resolution human pose estimation, body-part segmentation, surface nor…☆12Apr 28, 2026Updated 6 months ago
- An universal media loader for ComfyUI (Size, Image, Audio, Video)☆13Aug 27, 2026Updated 2 months ago
- Local ComfyUI workflow for watermark, mosaic and irregular overlay removal with Qwen Image 2.1 and SAM☆27Oct 31, 2026Updated 3 weeks ago
- ComfyUI nodes: turn a short idea into a checked Danbooru-tag prompt for the Anima model with a local LLM.☆14Nov 8, 2026Updated 2 weeks ago
- ComfyUI 视频剪辑工作台:多轨剪辑、MiniMax H3 生视频、人物替换、人体白模与动作迁移。个人使用免费,源码可见。☆38Updated this week
- Official repository of the paper "TopoRig: Topology-Agnostic Facial Rigging via Multi-Source Supervision".☆13Sep 20, 2026Updated 2 months ago
- Improved ReferenceLatent for ComfyUI — per-image strength, timestep gating, MediaPipe auto-masks, 1-4 image inputs. Works with Flux, Klei…☆37Jun 7, 2026Updated 5 months ago
Are these results useful?