THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Explore AI models 4

Provider Input Output License

Discover models worth your attention

minimax-h3-Camera-Motion-lora

Jojocodex

1. `_pruned` 文件放入 ComfyUI `models/loras/` 2. **LoraLoader** 加载，`strength_model` 建议 **0.8 ~ 1.0** - 0.8 运镜温和；1.0 运镜明确；>1.2 可能画面不稳 3. 底膜用 MiniMax-H3 视频工作流（pruned + int8 + convrot 版本） `camera_motion_提示词库.md` 里有 **55 条从训练素材原样提取的完整提示词**，按 9 类运镜组织（推近/拉远/推拉结合/环绕/跟拍/航拍/升降/摇镜/微距）， **直接复制粘贴即可**，效果与训练数据最接近。例如：

Translation queued · Showing source text

Video generation

Input Text→ Output Video

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

minimax-h3-spatial-physics-lora

Jojocodex

空间思维与物理逻辑 LoRA，基于 **MiniMax-H3**（Comfy-Org/MiniMax-H3）训练，让模型学会**纯物体**的空间关系与物理运动（碰撞、堆叠、掉落、遮挡等）。目前还是训练和测试阶段，一些素材片段以及打标问题导致LORA还不是特别稳定。下一阶段准备修复后重新训练。目前LORA也是可以使用，强度建议0.3 ~ 0.5。纯属是在原模型基础上稍微增强一点物理反馈。最新是重新训练到了wushu_spatial_physics_clean_3000_pruned.safetensors 版本。 1. 下载 `*.safetensors`，放入 ComfyUI `models/loras/` 2. LoraLoader 加载，strength 建议 0.8~1.0 3. 用空间/物理语言 prompt 描述物体运动

Translation queued · Showing source text

Video generation

Input Text→ Output Video

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

minimax-h3-wushu-action-lora

Jojocodex

武打动作 LoRA，基于 **MiniMax-H3**（Comfy-Org/MiniMax-H3）训练，让模型生成**人体武打/功夫动作**（拳、腿、踢、棍法等），专注人体打斗动作优化。个人在测试中4步和8步加速LORA偶尔会有画面糊的情况。Wushu-Action-LoRA 0.5的强度搭配0.3强度spatial-physics-lora，打斗的效果会更好。例： > `wushu_action,`（触发词）`a martial artist`（主体）`performing punches and kicks in fast combat, with explosive force`（招式与发力）`, indoor gym, medium shot, stable camera`（场景镜头）`, high quality, detailed`（画质） **① 动作主体** - `a martial artist` 武术家 / `a fighter` 格斗者 / `a wushu practitioner` 武术练习者 - `two fighters` 两名格斗者（对打） - `a martial artist with a staff` / `with a sword` / `with a spear` 持械

Translation queued · Showing source text

Video generation

Input Text→ Output Video

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

wushu-action-v7-minimax-h3-fl2va-ref2va-lora

Jojocodex

武打动作风格 LoRA（ComfyUI 即插即用）。基于 924 段精选武打片段（832×480 @ 24fps，专业招式术语三段式打标），以 **全量 int8-convrot DiT（未剪枝）+ bf16 Qwen3-VL 文本编码器** 训练 1000 步——当前量化精度最高的版本。触发词 `wushu_action`。 A wushu action style LoRA for MiniMax H3, trained 2000 steps on the **unpruned full int8-convrot DiT + bf16 Qwen3-VL text encoder** — the highest-fidelity quantization configuration. Trigger word: `wushu_action`. 之前PRUNED底座的训练的模型我都移除了，目前测得这版算是比较好一点的。但是表现我觉得还是没有达到我的预期，我觉得还是要再优化和增加素材，做一版新的LORA，届时会增加大量的运动动作。目前再整理再整理素材中，预计训练好也还需要2日时间。

Translation queued · Showing source text

Video generation

Input Image→ Output Video

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ

How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

Find your ideal AI model.

Explore AI models 4

minimax-h3-Camera-Motion-lora

minimax-h3-spatial-physics-lora

minimax-h3-wushu-action-lora

wushu-action-v7-minimax-h3-fl2va-ref2va-lora

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.