zephyr-7b-sft-full
alignment-handbook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 文本
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 84882
Mistral-nemo-3b-unhealed
Alignment-Lab-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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Neural-network-medium-5b-16k
Alignment-Lab-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。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Vid
Alignment-Lab-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。
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 ↗Llama-3.3-Tiny-Instruct-boolq
AlignmentResearch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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗FLUX.1-dev-Controlnet-Inpainting-Beta
alimama-creativeThis repository hosts an improved Inpainting ControlNet checkpoint for the alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha model, developed by the AlimamaCreative Team. 1. **1024 Resolution Support**: Capable of directly processing and generating 1024x1024 resolution images without additional upscaling steps, providing higher quality and more detailed output results. 2. **Enhanced Detail Generation**: Fine-tuned to capture and reproduce finer details in inpainted areas. 3. **Improved Prompt Control**: Offers more precise control over generated content through enhanced prompt interpretation. The following images were generated using a ComfyUI workflow (click here to download) with these settings: `control-strength` = 1.0, `control-end-percent` = 1.0, `true_cfg` = 1.0
译文排队中 · 当前显示来源原文
输入 图像→ 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 ↗FLUX.1-Turbo-Alpha
alimama-creativeThis repository provides a 8-step distilled lora for FLUX.1-dev model released by AlimamaCreative Team. This checkpoint is a 8-step distilled Lora, trained based on FLUX.1-dev model. We use a multi-head discriminator to improve the distill quality. Our model can be used for T2I, inpainting controlnet and other FLUX related models. The recommended guidance_scale=3.5 and lora_scale=1. Our Lower steps version will release later. - With alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta. Our distilled lora can be well adapted to the Inpainting controlnet, and the accelerated generated effect can follow the original output well.
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 ↗This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_albanian dataset. The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 30 - mixed_precision_training: Native AMP - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.14.7 - Tokenizers 0.15.0
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗albert-japanese
ALINEAR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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗albert-japanese-v2
ALINEAR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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗flash-sqlite
AlioLeuchtmann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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗qwen-3.5-sql-27B-Distill-2B
AlioLeuchtmann**WE HAVE A NEW MODEL scoring 73.73 EX on the hidden BIRD test set** https://huggingface.co/AlioLeuchtmann/flash-sqlite The smallest model in the top tier of the BIRD single-model leaderboard A 2B-parameter text-to-SQL model that outperforms models over 500× its size on the official BIRD benchmark. Qwen3.5-2B fine-tuned for SQLite text-to-SQL through execution-verified structured chain-of-thought distillation from a Qwen 27B teacher. Evaluated officially by the BIRD team on the hidden test set.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗small100
alirezamshSMaLL-100 is a compact and fast massively multilingual machine translation model covering more than 10K language pairs, that achieves competitive results with M2M-100 while being much smaller and faster. It is introduced in this paper(accepted to EMNLP2022), and initially released in this repository. The model architecture and config are the same as M2M-100 implementation, but the tokenizer is modified to adjust language codes. So, you should load the tokenizer locally from tokenization_small100.py file for the moment. Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Breton (br), Bosnian (bs), Catalan; Valencian (ca), Cebuano (ceb), Czech (cs), Welsh (cy), Danish (da), German (de), Greeek (el), English (en), Spanish (es), Estonian (et), Persian (fa), Fulah (ff), Finnish (fi), French (fr), Western Frisian (fy), Irish (ga), Gaelic; Scottish Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Croatian (hr), Haitian; Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Igbo (ig), Iloko (ilo), Icelandic (is), Italian (it), Japanese (ja), Javanese (jv), Georgian (ka), Kazakh (kk), Central Khmer (km), Kannada (kn), Korean (ko), Luxembourgish; Letzeburgesch (lb), Ganda (lg), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Burmese (my), Nepali (ne), Dutch; Flemish (nl), Norwegian (no), Northern Sotho (ns), Occitan (post 1500) (oc), Oriya (or), Panjabi; Punjabi (pa), Polish (pl), Pushto; Pashto (ps), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Russian (ru), Sindhi (sd), Sinhala; Sinhalese (si), Slovak (sk), Slovenian (sl), Somali (so), Albanian (sq), Serbian (sr), Swati (ss), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Thai (th), Tagalog (tl), Tswana (tn), Turkish (tr), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Wolof (wo), Xhosa (xh), Yiddish (yi), Yoruba (yo), Chinese (zh), Zulu (zu)
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗roberta-large-wanli
alisawuffles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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗rm-seed-42-harmfulness-flipped-05
AlisonWenNCTU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 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗BFS-Best-Face-Swap
AlissonerdxBFS is a collection of LoRAs for face, head, and body replacement across Qwen Image 2.1, Qwen Image Edit 2509/2511, Flux 2 Klein, Krea 2, and experimental LTX-2 workflows. Each release has its own base-model, input-order, prompt, and workflow contract. Use the guide for the exact version you are loading. - BFS Head V1 / V1.1 for Qwen Image 2.1 - BFS Body Swap V1.0 for Qwen Image 2.1 - Qwen Image Edit 2509/2511 - Flux 2 Klein - Krea 2 - Experimental LTX-2 weights - Use the LoRA with its matching base model whenever possible. - Follow the input order in the version guide; several BFS head releases intentionally use body first and reference face second. - Start at LoRA strength `1.0`, then adjust for the base model, resolution, and reference image. - The examples and workflows in this repository are demonstrations, not a guarantee of identical results on every image. - Do not use or share results involving public figures or people who have not given consent.
译文排队中 · 当前显示来源原文
输入 图像→ 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 ↗BFS-Best-Face-Swap-Video
Alissonerdx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 ↗CustomLightning
Alissonerdx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 ↗EditAnything
Alissonerdx> **Heads up.** These LoRAs are research experiments. They are far from > production-ready and will fail on many inputs. They are released for the > community to play with and break, not as a finished tool. 0. **Edit Anything v2 for LTX-2.5** — the current one, a plain instruction-editing IC-LoRA. Start here. *(built on LTX-2.5 22B)* 1. **Edit Anything v0.1 — motion transfer LoRA** (two ranks). *(LTX-2.3)* 2. **Edit Anything — no-reference multitask LoRA** (rank 256, prompt-driven only). *(LTX-2.3)* 3. **Reference video-to-video (Ref V2V) — experimental IC-LoRA + sidecar modules** (two builds). *(LTX-2.3)* Tracks 1-3 are **LTX-2.3** and are kept for reference. Track 0 is **LTX-2.5** and is the one being worked on.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗flux.1-dev-SRPO-LoRas
AlissonerdxThese LoRAs were extracted from **three sources**: - the original SRPO (Flux.1-Dev): tencent/SRPO - community checkpoint: rockerBOO/flux.1-dev-SRPO - community checkpoint (quantized/refined): wikeeyang/SRPO-Refine-Quantized-v1.0 They are designed to provide modular, lightweight adaptations you can mix with other LoRAs, reducing storage and enabling fast experimentation across ranks (8, 16, 32, 64, 128). Notes: - The Loras version for Nunchaku was converted using the official Nunchaku conversion tool but it is something experimental I still need to test and analyze the results, I do not recommend using it for now it is only for testing. - These loras allow you to use the quality of SRPO using the official flux dev as a base, without the need to use the base flux SRPO, that is, in my opinion, it is not very advantageous to use any of these loras + flux SRPO as a base, unless you want to apply the quality of, for example, SRPO RockerBOO in the base flux SRPO model. - The version I recommend is RockerBOO but I advise you to test the others, because the original version will give you different results than the other versions. - According to some reports it seems to work well with Flux Krea, the report was with rank 256, I haven't tested it yet to confirm.
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 ↗LTX-LoRAs
AlissonerdxThese LoRAs may cover different use cases over time, so this repository is not limited to inpainting only. These inpainting LoRAs were trained with a specific guide and mask setup, so input preparation during inference is important. After that, you need to use the **`LTXVAddGuideMulti`** node to pass the guide video into the model.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗Minimax-H3-ComfyUI
AlissonerdxExperimental LoRAs for MiniMax H3, packaged for ComfyUI and tested mainly with the `ref2va` weights. These are research models, not finished tools. Results vary substantially with the source clip, resolution, prompt and reference images. **Training adapter V2.** The Motion Transfer LoRAs were trained on top of ostris' training adapter V2 (`minimax_h3_ref2va_training_adapter_v2.safetensors`) kept frozen. They usually work without it, but loading the adapter first (strength 1) and the motion LoRA after it reproduces the training conditions; compare both on your clips.
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-26B-A4B-it-DFlash-GGUF-llama.cpp
Alittlehammmer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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗gemma-4-31B-it-DFlash-GGUF-llama.cpp
Alittlehammmer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 文本
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。