サイト内検索
AI モデル 84768
- tiny-random-DebertaV2Model↗
hf-tiny-model-private
- Llama-3.2-3B-Instruct-Q8_0-GGUF↗
hugging-quants
- Cyber-Tiel-Coder-35B-A3B-APEX-I-NanoPlus-GGUF↗
IsValorum
If you consider these releases to be of high quality and they help you in your day-to-day workflow, consider supporting on Ko-fi. Every contribution directly sustains future cloud compute hours and helps support my university studies. > These are complementary APEX-I releases, not alternate downloads of the same model. Each receives the same surgical tensor-by-tensor approach and a design suitable for full or partial system-RAM inference: > - **Cyber-Tiel-Coder-35B-A3B APEX-I-MiniPlus-V2.1** — specialist uncensored agentic coding MoE tuned for high-speed local development (14.75 GB / Q5–Q6 quality).
- whisper-large-v3-ct2↗
ivrit-ai
This is a Ctranslate2 (Faster Whisper) weight format of the ivrit-ai/whisper-large-v3 Please follow the Faster Whisper usage details here and use this model name.
- FlashVSR-v1.1↗
JunhaoZhuang
Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computation, and poor generalization to ultra-high resolutions. Our goal in this work is to make diffusion-based VSR practical by achieving **efficiency, scalability, and real-time performance**. To this end, we propose **FlashVSR**, the first diffusion-based one-step streaming framework towards real-time VSR. **FlashVSR runs at ∼17 FPS for 768 × 1408 videos on a single A100 GPU** by combining three complementary innovations: (i) a train-friendly three-stage distillation pipeline that enables streaming super-resolution, (ii) locality-constrained sparse attention that cuts redundant computation while bridging the train–test resolution gap, and (iii) a tiny conditional decoder that accelerates reconstruction without sacrificing quality. To support large-scale training, we also construct **VSR-120K**, a new dataset with 120k videos and 180k images. Extensive experiments show that FlashVSR scales reliably to ultra-high resolutions and achieves **state-of-the-art performance with up to ∼12× speedup** over prior one-step diffusion VSR models. First of all, huge thanks to the community for the fast adoption, feedback, and contributions to FlashVSR! 🙌 During community testing, we noticed that some third-party implementations of FlashVSR (e.g. early ComfyUI versions) do **not include our Locality-Constrained Sparse Attention (LCSA)** module and instead fall back to **dense attention**. This may lead to **noticeable quality degradation**, especially at higher resolutions. Community discussion: https://github.com/kijai/ComfyUI-WanVideoWrapper/issues/1441 ✅ The **official FlashVSR pipeline (this repository)**: - **Better preserves fine structures and details** - **Effectively avoids texture aliasing and visual artifacts**
- qwen-2.1-image-turbo-lora-set↗
kalle07
- Qwen3.5-4B-Uncensored-HauhauCS-Aggressive↗
kronoxxvx
- gpt3-kor-small_based_on_gpt2↗
kykim
- llama-3-Stheno-Mahou-8B-GGUF-IQ-Imatrix↗
Lewdiculous
- c69-h5↗
lfgidjg34dd
