MODEL PROFILE · 模型档案

Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI

robertbschuette · Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUI

A merged variant of MiniMax H3, a joint audio+video diffusion transformer (DiT) for ComfyUI, combining the strengths of the two source conditioning modes — first/last-keyframe (FL) and reference-driven (REF) — into a single checkpoint. A tensor-by-tensor comparison of the two checkpoints shows the large majority of weights — attention projections, MLPs, norms, patch projections, rotary embeddings, and the token refiner — are effectively identical between them. The meaningful differences are concentrated almost entirely in the per-block `adaln_proj` weights: the AdaLN modulation projections that route conditioning signal into the residual stream at each transformer block. This hybrid uses the **FL checkpoint as the base** for the entire network, with the **`adaln_proj` weights for transformer blocks 25–49 (the later half of the network) taken from the REF checkpoint** instead. Everything else — including the earlier-block `adaln_proj` weights, the final AdaLN projection, attention, MLPs, norms, and output heads — remains on FL throughout.

译文排队中,当前展示来源原文。

视频生成license:apache-2.0
上下文窗口来源未披露
输入 → 输出图像 → 视频
模型权重待核验
档案更新时间2026/11/2 19:16:17
OVERVIEW

模型介绍

A merged variant of MiniMax H3, a joint audio+video diffusion transformer (DiT) for ComfyUI, combining the strengths of the two source conditioning modes — first/last-keyframe (FL) and reference-driven (REF) — into a single checkpoint. A tensor-by-tensor comparison of the two checkpoints shows the large majority of weights — attention projections, MLPs, norms, patch projections, rotary embeddings, and the token refiner — are effectively identical between them. The meaningful differences are concentrated almost entirely in the per-block `adaln_proj` weights: the AdaLN modulation projections that route conditioning signal into the residual stream at each transformer block. This hybrid uses the **FL checkpoint as the base** for the entire network, with the **`adaln_proj` weights for transformer blocks 25–49 (the later half of the network) taken from the REF checkpoint** instead. Everything else — including the earlier-block `adaln_proj` weights, the final AdaLN projection, attention, MLPs, norms, and output heads — remains on FL throughout.

主要特点

特点摘要待依据来源补齐,不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价,不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价,请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用?

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗?

不是实时结算价格,而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

许可证:apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。