fibo-2.0-GGUF
molbal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 图像
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 12
Flux-3-Klein-GGUF
molbal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 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗ideogram-4-gguf
molbal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 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗krea2-gguf
molbalQuantized GGUF diffusion transformer weights for Krea 2, converted from the original BF16 releases for use with ComfyUI GGUF loader nodes. This repository provides GGUF files for two checkpoints of the Krea 2 model family: - `krea2_raw_bf16-*.gguf` — converted from krea/Krea-2-Raw, the base release checkpoint. - `krea2_turbo_bf16-*.gguf` — converted from krea/Krea-2-Turbo, the post-trained checkpoint with additional fine-tuning and distillation.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Kromoss-GGUF
molbal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 图像
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-GGUF
molbalThis repository contains GGUF quantizations for Lightricks/LTX-2.5, including the 22B distilled transformer model. 1. **Text-to-Video (T2V)**: * File: `workflows/video_ltx2_5_t2v-gguf.json` * Generates video directly from text prompts using the GGUF transformer. 2. **Image-to-Video (I2V)**: * File: `workflows/video_ltx2_5_i2v-gguf.json` * Animates a single source frame with synchronized audio and motion. 3. **First & Last Frame to Video (FLF2V)**: * File: `workflows/video_ltx2_5_flf2v-gguf.json` * Interpolates seamless video transitions between two keyframe images. Ensure you place the upstream support weights into their respective folders: * **Text Encoder / CLIP**: Gemma 4 12B with projection (`ComfyUI/models/clip/` or `text_encoders/`) * **Video VAE**: `ltx-2.5-video-vae-bf16.safetensors` (`ComfyUI/models/vae/`) * **Audio VAE**: `ltx-2.5-audio-vae-bf16.safetensors` (`ComfyUI/models/vae/`)
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 ↗MiniMax-H3-GGUF
molbalThis repository (`molbal/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. This repository includes quantized versions of both the `FL2VA` (First-and-last-frame mode) and `Ref2VA` (Omni-reference mode) base models. The FL2VA builds are pruned to FP8 first and then quantized to GGUF. * **FL2VA Models (pruned to FP8):** * `minimax_h3_fl2va_pruned_fp8_Q4_0.gguf` (11.4 GB) * `minimax_h3_fl2va_pruned_fp8_Q8_0.gguf` (20.2 GB) * `minimax_h3_fl2va_pruned_fp8_Q8_CR.gguf` (20.2 GB) * `minimax_h3_fl2va_pruned_fp8_U16G.gguf` (15.0 GB) * **Ref2VA Models:** * `minimax-h3-ref2va-Q4_0.gguf` (11.4 GB) * `minimax-h3-ref2va-Q8_0.gguf` (21.4 GB) * `minimax-h3-ref2va-Q8_CR.gguf` (20.2 GB) * `minimax-h3-ref2va-U16G.gguf` (15.0 GB)
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 ↗MiniMax-H3-Turbo-GGUF
molbalThis repository provides GGUF quantized versions and ComfyUI workflows for the **FL2VA Turbo 4-step v1.0 768p** variant of MiniMax-H3-Turbo. MiniMax H3 is an omni-modal generative system supporting unified text, image, video, and audio generation with native stereo audio. The Turbo distillation compresses inference down to **4 steps (NFE)** at **768p** resolution with shifted schedules. > [!IMPORTANT] > **Full Merged Checkpoints:** These GGUF files contain **full merged weights** (the base model + distilled turbo weights merged directly into a standalone model checkpoint), not separate LoRA adapters. You load them directly as diffusion models in ComfyUI without needing additional base weights or LoRA loaders.
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 ↗Minimax-Music3-GGUF
molbal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 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗MOSS-Image-GGUF
molbalThis repository contains GGUF quantizations of MOSS-Image-SFT, including the supplied Turbo variant. MOSS-Image generates images from natural-language prompts, tag sequences, and JSON layouts. The SFT model and conversion are based on the OpenMOSS release, which is licensed under Apache-2.0. File sizes are shown in GiB. Standard quants use common GGML formats. Proprietary quants use custom ConvRot formats supported by the `comfyui-gguf-reboot` loader nodes. Standard GGUF files can be loaded with compatible GGUF tools. Q8_CR and Q4_CR_L use custom quantization layouts and require the `comfyui-gguf-reboot` loader nodes. They are not compatible with general-purpose GGUF loaders.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Qwen-Image-2.1-GGUF
molbalQwen Image 2.1 is a diffusion transformer for text-to-image generation and image editing. It uses the Qwen3-VL 8B text encoder and supports image references through ComfyUI. It needs to be loaded with the GGUF Loader nodes. Load the model with the GGUF loader node from comfyui-gguf-reboot. Use the Qwen Image 2.1 workflow supplied by the installed ComfyUI version.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 图像
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Qwen-Image-2.1-Turbo is an accelerated checkpoint of Qwen-Image-2.1 for text-to-image generation and image editing with 8 denoising steps. It is a diffusion transformer for text-to-image generation and image editing. It uses the Qwen3-VL 8B text encoder and supports image references through ComfyUI. It needs to be loaded with the GGUF Loader nodes. Q4_0, Q4_K_M, Q6_K, and Q8_0 are standard GGML GGUF quantizations. Q8_CR is a custom GGUF INT8 ConvRot format supported by the comfyui-gguf-reboot loader nodes. It uses their native INT8 ConvRot execution path and is distinct from standard GGML Q8_0. Load GGUF files with the comfyui-gguf-reboot loader nodes. These nodes give the best performance and are required for the Q8_CR native INT8 ConvRot path. Use the Qwen Image 2.1 workflow supplied by the installed ComfyUI version.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 图像
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。