サイト内検索

AI モデル 2119

• anything-v5↗

  stablediffusionapi

  payload = json.dumps({ "key": "", "model_id": "anything-v5", "prompt": "actual 8K portrait photo of gareth person, portrait, happy colors, bright eyes, clear eyes, warm smile, smooth soft skin, big dreamy eyes, beautiful intricate colored hair, symmetrical, anime wide eyes, soft lighting, detailed face, by makoto shinkai, stanley artgerm lau, wlop, rossdraws, concept art, digital painting, looking into camera", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None })

• typhoon-asr-qwen-0.6b-ctx↗

  typhoon-ai

  Thai ASR with **prompt-based contextual biasing**: a LoRA fine-tune (merged, 0.80B params) of `Qwen/Qwen3-ASR-0.6B-hf` that accepts a list of names/terms in the system prompt, boosts the ones that are actually spoken, writes them with the **listed spelling**, and ignores the rest (distractor false alarm rate ≤.0004; non-speech probe 5/5). The economical tier: 2.6× smaller than the 1.7b for ~.09 recall. Plain transcription (CER%, same protocol: gigaspeech2 bench in-domain / TVSpeech out-of-domain 30-s talk-show): † single-digit repetition-loop utterances dominate (0.6b: one utt; Thonburian: three, excluding them 8.39).

• qwen-image-edit-multiple-angles-GGUF↗

  ChrisColeTech

  A pre-merged, quantized build of **Qwen-Image-Edit-2509** with two fine-tunes baked into the weights: Prompt: A giant full-body teddy bear wearing a plain white t-shirt. Print the exact logo from the input image onto the front of the t-shirt, large and clearly visible. Soft studio lighting, clean light-gray background, full-body shot, cute and detailed. Prompt: Show this exact teddy bear in one image as three separate full-body views in a row, evenly spaced: front view facing the camera, left side view, and back view facing away from the camera. In every view the head faces the same direction as the body — in the back view the head is also turned away from the camera and the face is completely hidden. Keep the character design, white t-shirt with the Qwen logo, lighting style, and light gray background perfectly consistent across all three views.

• adjoint_sampling↗

  facebook

• FastVideo-FastH3-Trim-Comfy↗

  FastVideo

  Original model repository: https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step FastH3 Trim is an experimental pruned FastH3 model: 42 transformer blocks instead of 50 and a rank-16 timestep conditioning, sampled in 8 steps. It is 4.2× smaller than base H3 and faster than FastH3 V2. Use the **FastVideo FastH3: Text to Video** template (ComfyUI 0.36.0 or later) and pick one of the files below in its `UNETLoader`. Keep the template's sampler settings: 8 steps, `res_multistep`, `simple`, and the `MiniMaxH3SigmaShift` node at 10 (video) and 3 (audio).

• Qwen3-4B-Alucard↗

  WasamiKirua

• timesfm-2.0-500m-pytorch↗

  Google

  TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting. * Paper: A decoder-only foundation model for time-series forecasting, ICML 2024. * Google Research blog * GitHub repo - It performs univariate time series forecasting for context lengths up to 2048 time points and any horizon lengths, with an optional frequency indicator. Note that it can go even beyond 2048 context even though it was trained with that as the maximum context. - It focuses on point forecasts. We experimentally offer 10 quantile heads but they have not been calibrated after pretraining. - It ideally requires the context to be contiguous (i.e. no "holes"), and the context and the horizon to be of the same frequency. In case there are nans we fill in the missing values with linear interpolation before calling the model.

• sam3↗

  Justin331

• bert-base-swedish-cased↗

  KB

  The National Library of Sweden / KBLab releases three pretrained language models based on BERT and ALBERT. The models are trained on aproximately 15-20GB of text (200M sentences, 3000M tokens) from various sources (books, news, government publications, swedish wikipedia and internet forums) aiming to provide a representative BERT model for Swedish text. A more complete description will be published later on. - **bert-base-swedish-cased** (*v1*) - A BERT trained with the same hyperparameters as first published by Google. - **bert-base-swedish-cased-ner** (*experimental*) - a BERT fine-tuned for NER using SUC 3.0. - **albert-base-swedish-cased-alpha** (*alpha*) - A first attempt at an ALBERT for Swedish. The examples below require Huggingface Transformers 2.4.1 and Pytorch 1.3.1 or greater. For Transformers<2.4.0 the tokenizer must be instantiated manually and the `do_lower_case` flag parameter set to `False` and `keep_accents` to `True` (for ALBERT).

• mHuBERT-147↗

  utter-project

  **MODEL DETAILS:** 3rd iteration, K=1000, HuBERT base architecture (95M parameters), 147 languages. mHuBERT-147 are compact and competitive multilingual HuBERT models trained on 90K hours of open-license data in 147 languages. Different from *traditional* HuBERTs, mHuBERT-147 models are trained using faiss IVF discrete speech units. Training employs a two-level language, data source up-sampling during training. See more information in our paper. 1. Summary 2. Training Data and Code 3. ML-SUPERB Scores 4. Languages and Datasets 5. Intermediate Checkpoints 6. Citing and Funding Information