[docs] Repair the version-specific model collection links (#2091)
Signed-off-by: mrhy7176 <129925370+mrhy7176@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Aryan Kumar <156166681+aryan5v@users.noreply.github.com>
This commit is contained in:
CloudGPU
co-authored by
Cursor Agent
Aryan Kumar
Cursor Agent
Aryan Kumar
parent
eee667df77
commit
794b8737fe
@@ -12,10 +12,10 @@
|
||||
- `2026/11/10`: Day-0 support for [PAN 2](https://huggingface.co/IFM/PAN2), a world model from IFM. See the [cookbook](https://haoailab.com/FastVideo/cookbook/pan/pan2/).
|
||||
- `2026/10/21`: Release [FastH3 Omni](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) (Ref2VA): reference-conditioned video-and-audio generation from a prompt plus ordered image, video and audio references, in eight fused forwards. It runs on consumer Blackwell (RTX 5090, RTX PRO 6000, DGX Spark — [NVFP4 QAD](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD)), on RTX 4090 (FP8) and on Apple Silicon (MLX). See the [cookbook](https://haoailab.com/FastVideo/cookbook/minimax-h3/) and the [inference guide](https://haoailab.com/FastVideo/inference/fasth3_omniref/).
|
||||
- `2026/10/06`: FastVideo now supports [Kandinsky 6](https://x.com/kandinskylab_ai/status/2107374635218055345) from Kandinsky Lab: text- and image-to-video with synchronized audio (base and 10-step distilled pi-Flow checkpoints) plus video super-resolution up to 4x. See the [Kandinsky 6 recipes](https://haoailab.com/FastVideo/cookbook/kandinsky6/).
|
||||
- `2026/10/06`: FastH3 V2 now runs on a single consumer machine: NVIDIA RTX 5090, RTX 4090 and RTX PRO 6000 GPUs, DGX Spark and Apple Silicon. We also release [FastH3 Trim](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4), an experimental pruned model that is 4.2× smaller than base H3 and runs in as little as 8 GB of GPU memory. Get the [models](https://huggingface.co/collections/FastVideo/fastvideo-fasth3) and read the [Blog](https://haoailab.com/blogs/fasth3-rtx/).
|
||||
- `2026/10/06`: FastH3 V2 now runs on a single consumer machine: NVIDIA RTX 5090, RTX 4090 and RTX PRO 6000 GPUs, DGX Spark and Apple Silicon. We also release [FastH3 Trim](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4), an experimental pruned model that is 4.2× smaller than base H3 and runs in as little as 8 GB of GPU memory. Get the [models](https://huggingface.co/collections/FastVideo/fasth3-v2) and read the [Blog](https://haoailab.com/blogs/fasth3-rtx/).
|
||||
- `2026/09/15`: Release [FastH3 8-Step V2](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2), an eight-forward data-free DMD2 checkpoint distilled from MiniMax-H3 with 80% Video Sparse Attention. Run it with `examples/inference/basic/basic_fasth3_8step.py` or the [FastH3 8-Step V2 recipe](https://haoailab.com/FastVideo/cookbook/minimax-h3/).
|
||||
- `2026/09/01`: FastH3 now runs locally on Apple Silicon through MLX and on NVIDIA DGX Spark through CUDA 13, including two-Spark inference. Follow the [FastH3 recipes](https://haoailab.com/FastVideo/cookbook/minimax-h3/) and read the [Blog](https://haoailab.com/blogs/fasth3-local/).
|
||||
- `2026/08/27`: [FastH3 Preview v1](https://haoailab.com/blogs/fasth3-preview/) is an open-weight 4-step sparse-distilled MiniMax-H3 model for synchronized video-and-audio generation, developed in collaboration with [Nuva Lab](https://nuvalab.ai/) and the [NVIDIA FastGen team](https://github.com/NVlabs/FastGen). Download the recommended [VSA / Data-Free weights](https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree), or see the [full FastH3 collection](https://huggingface.co/collections/FastVideo/fastvideo-fasth3).
|
||||
- `2026/08/27`: [FastH3 Preview v1](https://haoailab.com/blogs/fasth3-preview/) is an open-weight 4-step sparse-distilled MiniMax-H3 model for synchronized video-and-audio generation, developed in collaboration with [Nuva Lab](https://nuvalab.ai/) and the [NVIDIA FastGen team](https://github.com/NVlabs/FastGen). Download the recommended [VSA / Data-Free weights](https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree), or see the [FastH3 V1 collection](https://huggingface.co/collections/FastVideo/fasth3-v1).
|
||||
- `2026/08/19`: FastVideo now supports MLX on Apple Silicon with [FastMetal-QAD](https://huggingface.co/collections/FastVideo/fastmetal), a family of 1.3B, 5B, and 14B models optimized for Mac. Follow the [MLX install guide](https://haoailab.com/FastVideo/getting_started/installation/mlx/) and read the [Blog](https://haoailab.com/blogs/fastmetal/).
|
||||
|
||||
### More News
|
||||
@@ -31,7 +31,7 @@ FastVideo has the following features:
|
||||
- Data preprocessing pipeline for video, image, and text data
|
||||
- Distribution Matching Distillation (DMD2) stepwise distillation.
|
||||
- Sparse attention with [Video Sparse Attention](https://arxiv.org/pdf/2505.13389)
|
||||
- [Sparse distillation](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/) to achieve >50x denoising speedup
|
||||
- [Sparse distillation](https://haoailab.com/blogs/fastvideo_post_training/) to achieve >50x denoising speedup
|
||||
- Scalable training with FSDP2, sequence parallelism, and selective activation checkpointing.
|
||||
- Causal distillation through Self-Forcing
|
||||
- See this [page](https://haoailab.com/FastVideo/training/overview/) for the supported training workflows, and the [support matrix](https://haoailab.com/FastVideo/inference/support_matrix/) for supported models.
|
||||
@@ -65,7 +65,7 @@ To have a coding agent do the install, give it the [agent install prompt](https:
|
||||
|
||||
## Sparse Distillation
|
||||
|
||||
Sparse distillation reaches >50× denoising speedup. See the [distillation guide](https://haoailab.com/FastVideo/distillation/dmd/) and the [blog](https://hao-ai-lab.github.io/blogs/fastvideo_post_training/); the training recipes live under [`examples/distill/`](examples/distill/) with the [FastVideo Synthetic datasets](https://huggingface.co/FastVideo).
|
||||
Sparse distillation reaches >50× denoising speedup. See the [distillation guide](https://haoailab.com/FastVideo/distillation/dmd/) and the [blog](https://haoailab.com/blogs/fastvideo_post_training/); the training recipes live under [`examples/distill/`](examples/distill/) with the [FastVideo Synthetic datasets](https://huggingface.co/FastVideo).
|
||||
|
||||
## Dreamverse — Realtime Video Generation & Editing
|
||||
|
||||
|
||||
@@ -50,7 +50,7 @@ export default function FastModels() {
|
||||
<h2 id="checkpoint-catalog">Browse checkpoints</h2>
|
||||
<p>Pick the checkpoint that matches your runtime.</p>
|
||||
</div>
|
||||
<a href="https://huggingface.co/collections/FastVideo/fastvideo-fasth3">
|
||||
<a href="https://huggingface.co/collections/FastVideo/fasth3-v1">
|
||||
Earlier FastH3 releases <span aria-hidden="true">↗</span>
|
||||
</a>
|
||||
</header>
|
||||
|
||||
+2
-2
@@ -7,10 +7,10 @@ All FastVideo announcements, newest first. The README carries the latest items;
|
||||
- `2026/11/10`: Day-0 support for [PAN 2](https://huggingface.co/IFM/PAN2), a world model from IFM. See the [cookbook](https://haoailab.com/FastVideo/cookbook/pan/pan2/).
|
||||
- `2026/10/21`: Release [FastH3 Omni](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) (Ref2VA): reference-conditioned video-and-audio generation from a prompt plus ordered image, video and audio references, in eight fused forwards. It runs on consumer Blackwell (RTX 5090, RTX PRO 6000, DGX Spark — [NVFP4 QAD](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD)), on RTX 4090 (FP8) and on Apple Silicon (MLX). See the [cookbook](https://haoailab.com/FastVideo/cookbook/minimax-h3/) and the [inference guide](https://hao-ai-lab.github.io/FastVideo/inference/fasth3_omniref/).
|
||||
- `2026/10/06`: FastVideo now supports [Kandinsky 6](https://x.com/kandinskylab_ai/status/2107374635218055345) from Kandinsky Lab: text- and image-to-video with synchronized audio (base and 10-step distilled pi-Flow checkpoints) plus video super-resolution up to 4x. See the [Kandinsky 6 recipes](https://haoailab.com/FastVideo/cookbook/kandinsky6/).
|
||||
- `2026/10/06`: FastH3 V2 now runs on a single consumer machine: NVIDIA RTX 5090, RTX 4090 and RTX PRO 6000 GPUs, DGX Spark and Apple Silicon. We also release [FastH3 Trim](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4), an experimental pruned model that is 4.2× smaller than base H3 and runs in as little as 8 GB of GPU memory. Get the [models](https://huggingface.co/collections/FastVideo/fastvideo-fasth3) and read the [Blog](https://haoailab.com/blogs/fasth3-rtx/).
|
||||
- `2026/10/06`: FastH3 V2 now runs on a single consumer machine: NVIDIA RTX 5090, RTX 4090 and RTX PRO 6000 GPUs, DGX Spark and Apple Silicon. We also release [FastH3 Trim](https://huggingface.co/FastVideo/FastVideo-FastH3-Trim-8-Step-NVFP4), an experimental pruned model that is 4.2× smaller than base H3 and runs in as little as 8 GB of GPU memory. Get the [models](https://huggingface.co/collections/FastVideo/fasth3-v2) and read the [Blog](https://haoailab.com/blogs/fasth3-rtx/).
|
||||
- `2026/09/15`: Release [FastH3 8-Step V2](https://huggingface.co/FastVideo/FastVideo-FastH3-8-Step-V2), an eight-forward data-free DMD2 checkpoint distilled from MiniMax-H3 with 80% Video Sparse Attention. Run it with `examples/inference/basic/basic_fasth3_8step.py` or the [FastH3 8-Step V2 recipe](https://haoailab.com/FastVideo/cookbook/minimax-h3/).
|
||||
- `2026/09/01`: FastH3 now runs locally on Apple Silicon through MLX and on NVIDIA DGX Spark through CUDA 13, including two-Spark inference. Follow the [FastH3 recipes](https://haoailab.com/FastVideo/cookbook/minimax-h3/) and read the [Blog](https://haoailab.com/blogs/fasth3-local/).
|
||||
- `2026/08/27`: [FastH3 Preview v1](https://haoailab.com/blogs/fasth3-preview/) is an open-weight 4-step sparse-distilled MiniMax-H3 model for synchronized video-and-audio generation, developed in collaboration with [Nuva Lab](https://nuvalab.ai/) and the [NVIDIA FastGen team](https://github.com/NVlabs/FastGen). Download the recommended [VSA / Data-Free weights](https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree), or see the [full FastH3 collection](https://huggingface.co/collections/FastVideo/fastvideo-fasth3).
|
||||
- `2026/08/27`: [FastH3 Preview v1](https://haoailab.com/blogs/fasth3-preview/) is an open-weight 4-step sparse-distilled MiniMax-H3 model for synchronized video-and-audio generation, developed in collaboration with [Nuva Lab](https://nuvalab.ai/) and the [NVIDIA FastGen team](https://github.com/NVlabs/FastGen). Download the recommended [VSA / Data-Free weights](https://huggingface.co/FastVideo/FastVideo-FastH3-4-step-Preview-v1-VSA-DataFree), or see the [FastH3 V1 collection](https://huggingface.co/collections/FastVideo/fasth3-v1).
|
||||
- `2026/08/19`: FastVideo now supports MLX on Apple Silicon with [FastMetal-QAD](https://huggingface.co/collections/FastVideo/fastmetal), a family of 1.3B, 5B, and 14B models optimized for Mac. Follow the [MLX install guide](https://hao-ai-lab.github.io/FastVideo/getting_started/installation/mlx/) and read the [Blog](https://haoailab.com/blogs/fastmetal/).
|
||||
|
||||
## Earlier news
|
||||
|
||||
Reference in New Issue
Block a user