From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.
Experimental changes to refusal behavior may alter safeguards. Validate outputs and safety measures before use; follow applicable laws and the Apache-2.0 upstream terms.
Experimental changes to refusal behavior may alter safeguards. Validate outputs and safety measures before use; follow applicable laws and the Qwen Community License 1.0 upstream terms.
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
**DreamX-World** is a general-purpose world model for **interactive world simulation**. It generates diverse, high-fidelity worlds that users can explore, control, and transform with event prompts. **DreamX-World-5B** is the long-horizon autoregressive variant of DreamX-World. It is built on top of Wan2.2-TI2V-5B and generates videos from an input image, a text prompt, and keyboard-style camera action commands. Compared with the 5B-Cam variant, DreamX-World-5B uses chunk-wise causal autoregressive inference with KV caching, making long-horizon generation practical, including videos up to about 1 minute at 16 FPS. The model is trained with a scalable data engine on Unreal Engine data, gameplay footage, and real-world videos, together with camera estimation and data filtering. DreamX-World follows a progressive training pipeline for action control, open-ended event response, reinforcement-learning-based action following, and efficient inference through forcing and distillation.
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
Self Forcing trains autoregressive video diffusion models by **simulating the inference process during training**, performing autoregressive rollout with KV caching. It resolves the train-test distribution mismatch and enables **real-time, streaming video generation on a single RTX 4090** while matching the quality of state-of-the-art diffusion models. We tested this repo on the following setup: * Nvidia GPU with at least 24 GB memory (RTX 4090, A100, and H100 are tested). * Linux operating system. * 64 GB RAM. Note: * **Our model works better with long, detailed prompts** since it's trained with such prompts. We will integrate prompt extension into the codebase (similar to Wan2.1) in the future. For now, it is recommended to use third-party LLMs (such as GPT-4o) to extend your prompt before providing to the model. * You may want to adjust FPS so it plays smoothly on your device. * The speed can be improved by enabling `torch.compile`, TAEHV-VAE, or using FP8 Linear layers, although the latter two options may sacrifice quality. It is recommended to use `torch.compile` if possible and enable TAEHV-VAE if further speedup is needed.
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。
This model was converted to GGUF format from `petruhonk/Qwen3.8-9B-Distill-uncensored-heretic` using python code. Refer to the original model card for more details on the model. Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well. Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
> **工业级端侧极智大脑 · 离散扩散加速 (Discrete Diffusion) 物理熔铸 · Rank-2 SVD 级联双投影消融 · 26万 Token 真·双语海森满秩校准 · 消费级单卡（RTX 3060 12GB）满血点火** > **核心资产**：~4.76 GB 极智单文件纯血大脑（彻底剥离安全死锁 + 扩散提速 + IQ4_XS 端到端硬映射） > **极限吞吐**：RTX 3060 单卡实测 Prompt 预填充 **626.5 t/s**，自回归生成吞吐稳定在 **57.1 ~ 59.4 t/s**（满血输出高难渗透脚本与逆向工程代码） 本模型基于 `IFM/K2-Horizon-7B` 基座，**预先在物理层熔铸了 1.4GB 的 `Uno` 条件扩散适配器**，随后送入消融工厂进行全域安全剥离，最后实施 iMatrix 极限量化。实测战报如下： 1. **跨语言海森空间激活防坍缩**： - 校准语料采用严格的 **50% 纯正中文高熵长文本（COIG-CQIA 弱智吧+逻辑推导）+ 50% 英文推导（Alpaca）**，共计 262,144 个真实 Tokens； - 彻底破除了单一英文校准导致的中文表征正交子空间曲率坍缩，生成了极高纯度的 `imatrix.dat`。 2. **坚守 IQ4_XS (4.25 bpw) 黄金帕累托平衡点**： - 将 18GB 的庞然大物压缩至 **4.76 GB**，完美适配 12GB / 8GB 显存的消费级显卡，同时保证代数推理与代码生成满分闭环。
Translation queued · Showing source text
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
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。
Basic profile indexed · More details to follow
Adjust provider, category or input/output filters. New models are added continuously.
Adjust monthly token usage to compare estimated API costs.
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.
