Chinese-Emotion
Johnson8187基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗DISCOVER & COMPARE
Explore AI models 84999
Important: Tuned, and tweaked to match the legendary Qwen 3.6 27B FF711 (2300+ likes, 4 million+ downloads) this fine tune matches the stability and power at "arc-c" 709: (118 pts higher than Qwen 3.8 27B) (The OpenAI, Claude and Gemini "zone of intelligence") in 8 bit and 701 arc-c in 4 bit. This version is called TWIN-TURBO because it drastically reduces thinking tokens (by 1/2 to as LOW as 1/20), yet maintains output detail and quality. In other words while "reg" Qwen3.8 27B is thinking about "formatting" for a few 1000 tokens, this model is already done and waiting for more. This repo contains both "regular" and "MTP" Neo and NEO MAX GGUF quants. STRONGER/CTRL: Now with 5 reasoning modes (2 new - Spoon / Einstein), and 5 instruct modes (2 new - Spoon / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level). The most powerful, smartest open source multi-stage model fine tune for consumer hardware ever and BUILT on consumer hardware via Unsloth.
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Mage-VL-GGUF
JohnTdiCommunity GGUF conversion of microsoft/Mage-VL, including Q8_0 and Q4_K_M language backbones plus F16 and Q8_0 Mage-ViT projector weights and native Q8 StreamMind sidecars. *Mage-VL Studio showing a selected time range, static-text OCR, native runtime metrics and representative full-frame Highlights.* **Development disclosure:** code assistance and review were provided by OpenAI GPT-5.6 Sol. Final integration, testing and release decisions were made and verified by the repository maintainer.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MyanmarGPT
jojo-ai-mst基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MyanmarGPT-Chat
jojo-ai-mst基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗minimax-h3-Camera-Motion-lora
Jojocodex1. `_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
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗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
Input Image→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen2.5-Coder-14B-Instruct-bnb-4bit-bpmn-react
jojojo154152we基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗BUNNY_H3_Conditioning_Bridge
JOKER141基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗The previous action should create the starting state of the next one, instead of constantly resetting back to a neutral pose. Fight Flow V1 does not mainly teach new moves. It explores whether H3 can learn how two or more characters should actually fight together. Unlike regular LoRA training that mainly relies on captions, D-OPSD allows the Teacher to directly reference the target training video.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗H3-superhuman-combat-lora
JOKER141基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniMax-H3-Combat-Base-V2
JOKER141Combat Base V2 is a major upgrade over V1, focusing not only on faster combat, but on better action continuity, hit reactions, cumulative damage, spatial movement, and physical cause-and-effect. Combat Base V2 is no longer just a combat LoRA — it now works for both action and dialogue scenes, adding richer body movement, finer sound details, and stronger shot-to-shot continuity to character performance. Combat Base V2 不再只是一个武打 LoRA——它现在可文可武，在文戏中也能增加更丰富的身体动作、更细致的声音表现，以及更强的镜头与状态连续性。 If the LoRA looks muddy or less impactful than expected, check the sampler setup first. Sampler choice matters a lot for this LoRA. Core Physics & Motion Logic / 核心物理与动作逻辑 Combat Base V2 moves away from "attack → reset" loops into a continuous physical chain where missed strikes carry momentum, blocks change direction smoothly, and limbs separate cleanly without sticking. Hit reactions now persist and accumulate—sustained torso bending, lowered guards, and impaired mobility directly build toward convincing heavy finishers.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniMax-H3-Weapon-Combat-LoRA
JOKER141> These links are provided for convenient cloud deployment and one-click workflow access. Some links contain referral / invite codes that may support the creator at no additional cost to the user. More stable weapon trajectories, large swings, rotational attacks, recovery motions, and weapon-state inheritance. Stronger blocking, parrying, deflection, sliding contact, evasive interaction, and weapon separation.
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniMaxH3-GunFu-Gunfight-LORA
JOKER141基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗yolov8n-license-plate
joker5914基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Image→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗UNSEEN_Gemma_4_26B_NSFW-IQ2_M-GGUF
Jommarn-Ai基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Illustrious-XL-v2.0
JommarnUploaded by Jommarn. Includes full Diffusers format components: - `text_encoder/` (CLIPTextModel) - `text_encoder_2/` (CLIPTextModelWithProjection) - `tokenizer/` - `tokenizer_2/` - `unet/` - `vae/` - `scheduler/` - Single File: `Illustrious-XL-v2.0.safetensors`
Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗UNSEEN_Gemma_4_26B_NSFW-GGUF
Jommarn> 📌 **Base Model:** The full unquantized FP16/BF16 weights are hosted at 👉 **Jommarn/UNSEEN_Gemma_4_26B_NSFW** (surgically abliterated from `google/gemma-4-26B-A4B-it`). > > ⚡ **This Repository:** Dedicated to optimized **Quantized (2-bit / 3-bit / 4-bit / 5-bit / 6-bit / 8-bit / 16-bit Master)** and **GGUF** deployment formats for consumer GPUs, Apple Silicon Mac, and `llama.cpp` serving. - **2-bit (`IQ2_M` ~9.67GB):** ~8–10GB VRAM (e.g., RTX 3060 12GB, RTX 4060, Mac 16GB) — *Extreme Efficiency* - **3-bit (`IQ3_M` ~12.4GB):** ~12–14GB VRAM (e.g., RTX 4070 12GB, RTX 3080, Mac 16GB) — *High Efficiency* - **4-bit (`Q4_K_M` ~15.6GB / `NF4`):** ~16–18GB VRAM (e.g., RTX 3090, RTX 4090, NVIDIA L4) — *Recommended Standard* - **5-bit (`Q5_K_M` ~18.3GB):** ~20–22GB VRAM (e.g., RTX 3090/4090 24GB, A10G 24GB) — *Balanced High-Quality* - **6-bit (`Q6_K` ~22.6GB):** ~24–26GB VRAM (e.g., RTX 4090 24GB, A100 40GB) — *High Precision* - **8-bit (`Q8_0` ~28.0GB / `INT8`):** ~28–30GB VRAM (e.g., 2x RTX 3090/4090, A100 40GB/80GB) — *99.9% Lossless* - **16-bit (`BF16` ~50.5GB):** ~52GB VRAM (e.g., A100 80GB, Mac Studio 64GB/128GB) — *100% Uncompressed Master* - **Vision Projector (16-bit):** `mmproj-gemma4-vision-f16.gguf` (~1.11GB) — *Must be loaded with `--mmproj` for image perception in llama.cpp/GGUF.* - **GGUF Weights:** Available at 👉 **Jommarn/UNSEEN_Gemma_4_26B_NSFW-GGUF** > ⚠️ **Important for GGUF Users:** To enable image understanding in `llama.cpp` or LM Studio, you **MUST** download and pass `mmproj-gemma4-vision-f16.gguf` alongside the main model. Without it, the model will operate strictly as a text-only LLM!
Input Text · Image→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-Flash-Next-AWQ-INT4-FP8PLE
Jon-Nielsen基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗MiniMax-H3
jon52638973基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗Qwen3.8-27B-DFlash2-b32
JonasLoos基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
Basic profile indexed · More details to follow
Input Text→ Output Text
Price not verifiedCheck multimodal and channel pricing separately
View details ↗No matching models
Adjust provider, category or input/output filters. New models are added continuously.
COST EXPLORER
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
1 M = 1 million tokens · USD
Compares base text-token rates within the same channel
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
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.