LTX-2.3-uncensored-v1.4-FP8
0xSojalSec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。
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 792
LTX-2.3-Audio-Reactive-LORA
100percentrobot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。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗fg_hg
1c1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。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗An **NVFP4 (4-bit) Qwen3-VL-32B text encoder** for MiniMax-H3, made with `convert-to-quant`. It is a drop-in replacement for the H3 conditioning text encoder (ComfyUI `CLIPLoader`, type `minimax`). The H3 video weights are unchanged — only the text encoder is quantized to 4-bit, to bring the full H3 stack onto consumer GPUs. This encoder deliberately keeps more of the network in bf16 than a minimum-size 4-bit encoder does. The `--qwen_vlm` filter protects — at bf16 — the token embeddings, the **first and last language layers**, and the **entire vision tower**, quantizing only the middle language-layer linears to NVFP4. The result is 16.64 GiB, about 2 GiB above the most aggressively quantized community NVFP4 encoders (≈14.6 GiB, e.g. the AWQ-quantized encoder in `Comfy-Org/MiniMax-H3`), in exchange for leaving the precision-sensitive layers (embeddings, boundary layers, vision) untouched. It is a fidelity-first tradeoff: spend ~2 GiB more VRAM to keep the layers that most affect conditioning at full precision. Everything still fits a 24 GB card with offload. Everything is held constant except encoder precision — the bf16 encoder vs this NVFP4 encoder, same prompts, same seeds, same DiT — over a 16-clip paired set.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LTX-Video-0.9.1-diffusers
a-r-r-o-w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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗MiniMax-H3-Acc-LoRAs
A20labs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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Sulphur-2-base
a4rtx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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Wan2.2-Distill-Loras
AakashTestCheck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。
基础资料已收录 · 缺失资料后续补充
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Minimax_h3_hybrid
abakanai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。
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗minimax-h3-int8
abhishekchohan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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗FastH3-Omni-GGUF
AbirayHigh-precision **GGUF quantizations** of **FastVideo/FastH3-Omni-Comfy** (`fasth3_omniref_8step_pruned_bf16.safetensors`), the **8-step consistency-distilled Omni-Reference (`Ref2VA`)** model built on **MiniMax-H3** by FastVideo (Hao AI Lab) in collaboration with Nuva Lab and Reactor. Unlike standard naive quantizations that crush timestep modulation tables and output heads into low-bit blocks, **this GGUF suite uses hybrid precision shielding** to keep critical audio/video decoding heads, 32-head PDD (Progressive Distillation) offsets, and AdaLN interpolation tables in **lossless `FP32`**, while compressing the 50-block DiT + Video Sparse Attention (`VSA`) backbone for consumer RTX GPUs. All files are converted from the **44.24 GB Pruned BF16** checkpoint (`FastVideo/FastH3-Omni-Comfy`) compatibility with `city96/ComfyUI-GGUF`.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This repository contains the **LTX-Video 2.3 (v1.1)** Distilled weights, quantized to **GGUF** format. GGUF offers highly efficient inference and excellent memory scaling, allowing you to run this heavy 22B parameter model on consumer hardware by splitting the workload between your GPU (VRAM) and CPU (System RAM). To use these GGUF files in **ComfyUI**, you will need a custom node suite that supports loading GGUF models (such as `ComfyUI-GGUF`).
译文排队中 · 当前显示来源原文
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LTX-2.5-Distilled-GGUF
AbirayThis repository provides quantized GGUF formats of the distilled transformer from Lightricks/LTX-2.5. These weights are highly optimized for local execution, allowing you to run high-fidelity video and audio generation workflows on hardware with memory constraints while retaining the core visual fidelity of the original base model. LTX-2.5 operates on a split-component architecture. To run these GGUF diffusion models in environments like ComfyUI or local Python pipelines, you must also fetch the official Text Encoders and VAEs directly from the upstream Lightricks/LTX-2.5 repository. Download these from the `text_encoders` directory:
译文排队中 · 当前显示来源原文
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LTX2.3-10Eros-1.3-GGUF
Abiray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。
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗LTX2.3-10Eros-GGUF
Abiray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。
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗MiniMax-H3-GGUF
AbirayThis repository (`Abiray/MiniMax-H3-GGUF`) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. --- If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the **MiniMax-H3-Pruned-GGUF** repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. **Available Pruned Quants:** | Bit Size | Quantization Type | File Size | | :--- | :--- | :--- | | **3-bit** | `Q3_K_M` | 8.9 GB | | **4-bit** | `Q4_K_S`, `Q4_K_M` | 11.6 GB | | **5-bit** | `Q5_K_S`, `Q5_K_M` | 14.1 GB | | **6-bit** | `Q6_K` | 16.7 GB | | **8-bit** | `Q8_0` | 21.6 GB | --- This repository includes quantized versions of both the `FL2VA` (First-and-last-frame mode) and `Ref2VA` (Omni-reference mode) base models. * **FL2VA Models:** * `MiniMax-H3-FL2VA-Q3_K_M.gguf` (15.6 GB) * `MiniMax-H3-FL2VA-Q3_K_S.gguf` (15.6 GB) * `MiniMax-H3-FL2VA-Q4_0.gguf` (18.6 GB) * `MiniMax-H3-FL2VA-Q4_K_M.gguf` (19.9 GB) * `MiniMax-H3-FL2VA-Q4_K_S.gguf` (19.9 GB) * `MiniMax-H3-FL2VA-Q5_0.gguf` (22.8 GB) * `MiniMax-H3-FL2VA-Q5_K_M.gguf` (23.9 GB) * `MiniMax-H3-FL2VA-Q5_K_S.gguf` (23.9 GB) * `MiniMax-H3-FL2VA-Q6_K.gguf` (28.2 GB) * `MiniMax-H3-FL2VA-Q8_0.gguf` (36 GB) * **Ref2VA Models:** * `MiniMax-H3-Ref2VA-Q3_K_M.gguf` (15.6 GB) * `MiniMax-H3-Ref2VA-Q3_K_S.gguf` (15.6 GB) * `MiniMax-H3-Ref2VA-Q4_0.gguf` (18.6 GB) * `MiniMax-H3-Ref2VA-Q4_K_M.gguf` (19.9 GB) * `MiniMax-H3-Ref2VA-Q4_K_S.gguf` (19.9 GB) * `MiniMax-H3-Ref2VA-Q5_0.gguf` (22.8 GB) * `MiniMax-H3-Ref2VA-Q5_K_M.gguf` (23.9 GB) * `MiniMax-H3-Ref2VA-Q5_K_S.gguf` (23.9 GB) * `MiniMax-H3-Ref2VA-Q6_K.gguf` (28.2 GB) * `MiniMax-H3-Ref2VA-Q8_0.gguf` (36 GB) * `qwen3vl_32b_minimax_h3_int4_convrot.safetensors` (15 GB) * `qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors` (27.1 GB) * `qwen3vl_32b_minimax_h3-Q4_K_M.gguf` (14.6 GB) * `minimax_h3_audio_vae_fp32.safetensors` (605 MB) * `minimax_h3_video_vae_fp16.safetensors` (5.21 GB) * **H3-Base-FL2VA:** First-and-last-frame mode. Supports zero, one, or two input images. * No image input: T
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This hybrid model fuses the crisp visual quality, motion dynamics, and clean audio of **FL2VA** with the persistent multi-image character conditioning of **Ref2VA** using a **rank-1024 delta weight merge ($\Delta W_{r=1024}$)** on the pruned 20.1B parameter MiniMax-H3 architecture. With these GGUFs, you can now run reference-conditioned MiniMax-H3 locally on consumer GPUs (16 GB – 24 GB VRAM) with minimal quality loss. Place the downloaded `.gguf` file into: ComfyUI/models/diffusion_models/ *(or `ComfyUI/models/unet/`)*
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗GGUF quantized versions of **WarmBloodAban/Minimax-h3_Singularity**, a community fine-tune of MiniMax H3 specialized in enhanced visual fidelity — HDR clarity, distant-face restoration, cleaner skin, stronger action motion, and improved VFX. These quantizations reduce VRAM requirements for use with ComfyUI, enabling local inference on consumer GPUs. Place the downloaded `.gguf` file in your ComfyUI `models/unet/` directory (or `models/diffusion_models/` depending on your ComfyUI-GGUF fork). You will also need the following components: For accelerated generation, you can optionally pair this model with the **minimax_h3_ref2v_turbo_4step_v0.1** LoRA, which enables 4-step fast inference.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Pruned and optimized `.safetensors` versions of WarmBloodAban/Minimax-H3 Singularity, formatted for native ComfyUI custom nodes (such as `comfyui-mixed-quantizer` and native INT8 loaders). 1. Place your chosen `.safetensors` file into your ComfyUI models folder: `ComfyUI/models/diffusion_models/` 2. Load the model using your preferred native ComfyUI loader or mixed-quantizer custom nodes. 3. Pair it with the Qwen3-VL text encoder and MiniMax-H3 Video + Audio VAEs.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗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。
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗SCAIL-2-GGUF
AbirayThis repository contains GGUF quantizations of **SCAIL-2**, the cutting-edge end-to-end controlled character animation and video motion-transfer model built on the Wan 2.1 14B architecture by zai-org. These weights are specifically optimized to execute the heavy SCAIL-2 Diffusion Transformer (DiT) inside ComfyUI at a fraction of the native FP16/FP8 VRAM overhead. 1. **Required Loader:** Install city96's ComfyUI-GGUF extension. 2. **Node Placement:** Use the `Unet Loader (GGUF)` node. 3. **File Path:** Download your preferred quant from this repository and drop it into: ComfyUI/models/unet/ ---
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Sulphur-2-base-GGUF
Abiray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。
输入 文本→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗This repository contains **GGUF-quantized versions** of the LightX2V Distilled Wan2.2 14B Image-to-Video Model. By quantizing the ultra-fast 4-step distilled models into the GGUF format, this repository allows for drastically reduced VRAM/RAM requirements while maintaining near real-time, high-performance video generation. We provide quantizations ranging from heavily compressed (Q3) to near-lossless (Q8) to fit your specific memory and quality requirements. Both **High Noise** and **Low Noise** versions are available.
译文排队中 · 当前显示来源原文
输入 图像→ 输出 视频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。