JOKER141/BUNNY_H3_Conditioning_Bridge
text-to-video model by JOKER141
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
V2 is not a simple dataset expansion of V1 — the entire training pipeline was rebuilt from the ground up. V2 并不是简单扩大 V1 的数据集，而是重新构建了整套训练流程。 The full V2 dataset contains 133,200 records: 109,200 high-dynamic hard cases and 24,000 preservation anchors. V2 完整数据集共 133,200 条：109,200 条高动态 Hard Cases + 24,000 条 Preservation Anchors。 The dataset covers 29 high-dynamic semantic families, with 26 families used for training and 3 Sequence-Causal families excluded from training. 整个数据集覆盖 29 个高动态语义类别，其中 26 个参与训练，另外 3 个 Sequence-Causal 类别不参与训练。 Covered concepts include pursuit, overtaking, braking and retaking, weapon loss and recovery, occlusion re-identification, momentum inheritance, knockback, rebound, catching, relative facing, ricochet geometry, route merging, multi-actor handoff, cover relationships, combat-state inheritance, weapon reclaim, parkour routing, vertical landing, vehicle-passenger relationships, aerial interception, wall rebound, multi-actor ordering, and more. 覆盖概念包括：追逐、超车、刹停再追、武器脱手与回收、遮挡后身份恢复、动量继承、击飞、反弹、接住、相对朝向、弹道与反弹几何、路线汇合、多人交接、掩体关系、战斗状态继承、武器回收、跑酷路线、垂直落地、车辆与乘员关系、空中拦截、撞墙反弹、多人动作排序等。 Compared with V1, V2 expands the target from basic action ownership and continuity into a much broader high-dynamic semantic space. 相比 V1，V2…
Read the full model card ↗ · Preview checked 2026-10-28T13:37:07.791Z
Inside the original model card — Document outline
- V2 — Update Notes
- V2 — 更新说明
- 🐇 BUNNY H3 Semantic Bridge V1
- 动作修复都无法解决的问题
- 📦 Installation
- 📦 安装
- 1. Install the custom node
- 1. 安装节点
- 2. Install the model
- 2. 安装模型
- 然后重启 ComfyUI。
- If installed through ComfyUI Manager, the folder name may appear as bunny-h3-semantic-bridge. This i
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
JOKER141/BUNNY_H3_Conditioning_Bridge is a text-to-video model repository published by JOKER141 on Hugging Face. The source reports the minimax-h3 library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-video
- Library
- minimax-h3
- Recent downloads (30 days)
- 3,912
- Cumulative likes
- 41
- Hugging Face trending score
- 2
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-09-13T23:03:26.000Z
- Last modified
- 2026-09-23T06:20:35.000Z
Compatibility and lineage
Language coverage was not reported.
Reported base models: MiniMaxAI/MiniMax-H3
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-16T06:43:24.841Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
QuantStack/Wan2.2-TI2V-5B-GGUF
QuantStack/Wan2.2-T2V-A14B-GGUF