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。
基本情報を収録・詳細は順次追加
言語から画像、オープンウェイトからAPIまで。能力と実際の費用を比較。
次のアイデアに合うAIを見つけましょう。
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
**FLUX.2 [dev] Turbo** is a distilled LoRA adapter for [FLUX.2 [dev]](https://huggingface.co/black-forest-labs/FLUX.2-dev) that enables high-quality image generation in just **8 inference steps**. This model inherits the [FLUX [dev] Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.txt) from the base model.
翻訳待ち・原文を表示
Virtual clothing try-on LoRA for Flux Klein 9b Edit. Given a person image and clothing reference images, generates a realistic result of the person wearing the specified outfit. **Try it now:** - Playground (direct) — upload your images and run the model - Workflow with LLM — auto-generates the prompt for you > Example images shown on this page were generated using Nano Banana Pro and are not part of the training data.
翻訳待ち・原文を表示
Best paired with the render‑to‑real endpoint's `enable_detail_refine` option (extra 2× spatial‑upscale + detailer pass). File: `3DREAL-strong-v2.safetensors`. Made with Strong v2 — a 1930s chase short where every shot starts as a Blender blockout (action, cameras and cuts owned by the 3D scene): This is an **IC‑LoRA** (in‑context LoRA) for **LTX‑2.3** that turns a rough grey 3D viewport animation (a simple low‑poly blockout) into a fully **photorealistic, film‑quality** video, while keeping the **exact composition, camera move and layout** of the input.
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
A LoRA adapter for MiniMax H3 specialized in realistic people: faces that hold up in close-up, natural skin texture, believable expressions and gestures, film-style lighting and documentary camera movement. 19 pairs, **same prompt, same seed, adapter on vs off** — the only variable is the LoRA. The trigger word is present on both sides, so it is not doing the work. Each pair plays the base model first, then freezes and dims while the adapted version plays beside it. Close-up talking faces, arguments, several people speaking at once, weathered skin, children, ritual and travel scenes. Nothing cherry-picked from a larger render batch: these are the pairs that were kept, in order. (download the comparison, 197s, 1920x1080)
翻訳待ち・原文を表示
> **Multi-angle camera control LoRA for Qwen-Image-Edit-2511** > > 96 camera positions • Trained on 3000+ Gaussian Splatting renders • Built with fal.ai **This is the first multi-angle camera control LoRA for Qwen-Image-Edit-2511.** While Qwen-Image-Edit-2511 has built-in viewpoint capabilities, this LoRA provides:
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
The **Fine-Tuned Vision Transformer (ViT)** is a variant of the transformer encoder architecture, similar to BERT, that has been adapted for image classification tasks. This specific model, named "google/vit-base-patch16-224-in21k," is pre-trained on a substantial collection of images in a supervised manner, leveraging the ImageNet-21k dataset. The images in the pre-training dataset are resized to a resolution of 224x224 pixels, making it suitable for a wide range of image recognition tasks. During the training phase, meticulous attention was given to hyperparameter settings to ensure optimal model performance. The model was fine-tuned with a judiciously chosen batch size of 16. This choice not only balanced computational efficiency but also allowed for the model to effectively process and learn from a diverse array of images. To facilitate this fine-tuning process, a learning rate of 5e-5 was employed. The learning rate serves as a critical tuning parameter that dictates the magnitude of adjustments made to the model's parameters during training. In this case, a learning rate of 5e-5 was selected to strike a harmonious balance between rapid convergence and steady optimization, resulting in a model that not only learns swiftly but also steadily refines its capabilities throughout the training process.
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
The **Fine-Tuned T5 Small** is a variant of the T5 transformer model, designed for the task of text summarization. It is adapted and fine-tuned to generate concise and coherent summaries of input text. The model, named "t5-small," is pre-trained on a diverse corpus of text data, enabling it to capture essential information and generate meaningful summaries. Fine-tuning is conducted with careful attention to hyperparameter settings, including batch size and learning rate, to ensure optimal performance for text summarization. During the fine-tuning process, a batch size of 8 is chosen for efficient computation and learning. Additionally, a learning rate of 2e-5 is selected to balance convergence speed and model optimization. This approach guarantees not only rapid learning but also continuous refinement during training.
翻訳待ち・原文を表示
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。
基本情報を収録・詳細は順次追加
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。
基本情報を収録・詳細は順次追加
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。
基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。
Drag this image into ComfyUI to load the example workflow. I've done limited testing so far on running the model, so take that workflow and the following advice with a grain of salt. bigASP V2.5 is an intermediary experiment I wanted to run while I prepared for V3. Like V2, it is a large scale finetune from SDXL, and follows most of V2's approach except for these bizarre tweaks: 1. Dataset expanded from 6.7M to 13M images by including additional sources as well as, significantly, anime. Why? Because I wanted to see if the model could dual purpose for both photoreal gens and anime gens. Also I wanted to see if photoreal gens could benefit from the more varied concepts present in anime/furry/etc images. 2. Training length expanded from 40M samples to 150M samples. One of my theories for the tempermental behavior of V2 is the scale of the training. Models like Pony v6 had a much larger amount of training. 150M samples brings V2.5 within the ballpark of that class of model. 3. Using JoyCaption Beta One instead of the Pre-Alphas used in V2. Beta One has more modes, and I tweaked its language and verbage quite a bit, so hopefully V2.5 is less sensitive to prompts. 4. Swapping SDXL's training objective over to Rectified Flow Matching like more modern models (i.e. Flux, Chroma, etc). This was done for two reasons. One, Flow Matching makes higher quality generations. And two, it allowed me to ditch SDXL's broken noise schedule. That latter bit greatly enhances the model's ability to control the overall structure of generations, resulting in less mangled mess generations and extra limbs. It also allows V2.5 to generate more dynamic range from very dark images to very bright images.
翻訳待ち・原文を表示
提供元・分類・入出力の条件を変更してください。新しいモデルを随時追加しています。
月間トークン数を調整してAPI費用を比較。
収集済みの比較可能な100万トークン当たり米ドル料金です。キャッシュ割引、段階料金、追加推論出力、税金は含みません。最新料金は出典で確認してください。
入力・出力・キャッシュ料金を分け、同じ用途と使用量で総費用を比較します。画像・音声・動画は枚数、時間、解像度で課金される場合があります。
必ずしもそうではありません。バージョンごとのライセンス、商用制限、ポリシーを確認してください。自前運用には計算資源と保守費用も必要です。
順位はテスト、バージョン、評価方法によります。実際の業務データで精度、遅延、安定性、費用を比較してください。