Krea Realtime 14B is distilled from the Wan 2.1 14B text-to-video model using Self-Forcing, a technique for converting regular video diffusion models into autoregressive models. It achieves a text-to-video inference speed of **11fps** using 4 inference steps on a single NVIDIA B200 GPU. For more details on our training methodology and sampling innovations, refer to our technical blog post. - Our model is over **10x larger than existing realtime video models** - We introduce **novel techniques for mitigating error accumulation,** including **KV Cache Recomputation** and **KV Cache Attention Bias** - We develop **memory optimizations specific to autoregressive video diffusion models** that facilitate training large autoregressive models - **Our model enables realtime interactive capabilities**: Users can modify prompts mid-generation, restyle videos on-the-fly, and see first frames within 1 second Krea realtime allows users to stream real videos, webcam inputs, or canvas primitives into the model, unlocking controllable video synthesis and editing
Explore AI models 85001
punctuate-all
kredorThis is based on Oliver Guhr's work. The difference is that it is a finetuned xlm-roberta-base instead of an xlm-roberta-large and on twelve languages instead of four. The languages are: English, German, French, Spanish, Bulgarian, Italian, Polish, Dutch, Czech, Portugese, Slovak, Slovenian. 0 0.99 0.99 0.99 73317475 . 0.94 0.95 0.95 4484845 , 0.86 0.86 0.86 6100650 ? 0.88 0.85 0.86 136479 - 0.60 0.29 0.39 233630 : 0.71 0.49 0.58 152424 accuracy 0.98 84425503 macro avg 0.83 0.74 0.77 84425503 weighted avg 0.98 0.98 0.98 84425503
stable_diffusion_weights
kremeth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
gemma-4-26B-A4B-it-GGUF
Kremon96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
wav2vec2-large-xlsr-korean
kresnik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。
qwen36-35b-a3b-colibri-i4-gs64
Kreuzzelgcolibri container for **Qwen3.6-35B-A3B**, quantized to **group-scaled int4** (one f32 scale per 64 input elements per row, `expert_gs=64`, ~22 GB). This is the higher-accuracy sibling of the per-row container `Kreuzzelg/qwen36-35b-a3b-colibri-i4`: in a controlled A/B against an int8 anchor it cuts the first-token logit error by **~44 %** (mean cosine 0.98777 → 0.99313 over 4 prompts). Same self-contained layout (bundled `tokenizer.json`, flat `config.json`). **Which one should I use?** The per-row container is the current PR default and runs on the plain `qwen36-engine` branch. This gs64 container needs the group-scaled expert path (`matmul_q_gs`), which lives on the `gs64-ab` branch (pending upstream). If you're on that branch and want the best quality, use this one; the container size grows ~10 % (20 → 22 GB) and decode speed is unchanged. Behavior: greedy 512-token generation on 4 reasoning prompts showed **no degenerate loops** on either container — the group scaling is a quality improvement here, not a fix for a runaway-generation bug.
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
krinny-7b
krinny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
social-story-gemma4-e2b-v5
Kris0404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
social-story-gemma4-e2b-v5-lite
Kris0404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
buildfail-slm-qwen7b-adapter
krishna1707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
Qwen3.8-Flash-Next-DS4-Mixed-Q3
Krissaito470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
dots.ocr-1.5
kristaller486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
ip-adapter-faceid-plusv2_sdxl.bin
kristian1515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
huginn-0125
KristianS7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
Ouro-1.4B
KristianS7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。
Ouro-1.4B-Thinking
KristianS7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
Ouro-2.6B
KristianS7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
Ouro-2.6B-Thinking
KristianS7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
banano-kirtis-v2
kristijonas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
kmynas-parakeet-lt-v4
kristijonas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
No matching models
Adjust provider, category or input/output filters. New models are added continuously.
Great models. Clear costs.
Adjust monthly token usage to compare estimated API costs.
Compares base text-token rates within the same channel
Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.
Understand before you choose
How should API prices be compared?+
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.
Do open weights mean free commercial use?+
Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.
Is the top-ranked model the best for me?+
Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.