Use FastH3 Omni name and add local AI recipes

README.md

@@ -8,15 +8,15 @@ tags:
 - comfyui
 - diffusion-single-file
 - minimax-h3
-- omniref
+- fasth3-omni
 - reference-to-video
 - nvfp4
 - qad
 ---
 
-# FastH3 OmniRef NVFP4 QAD for ComfyUI
+# FastH3 Omni NVFP4 QAD for ComfyUI
 
-The ComfyUI-native NVFP4 QAD diffusion model for FastH3 OmniRef. It generates video with synchronized 32-kHz stereo audio from a prompt and ordered image, video and audio references in eight sampling steps.
+The ComfyUI-native NVFP4 QAD diffusion model for FastH3 Omni. It generates video with synchronized 32-kHz stereo audio from a prompt and ordered image, video and audio references in eight sampling steps.
 
 [Release collection](https://huggingface.co/collections/FastVideo/fasth3-omniref) · [BF16 release](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) · [Shared ComfyUI components](https://huggingface.co/FastVideo/FastH3-OmniRef-Comfy)
 
@@ -28,7 +28,7 @@ Place `fasth3_omniref_qad_nvfp4_comfy.safetensors` in:
 ComfyUI/models/diffusion_models/fasth3_omniref_qad_nvfp4_comfy.safetensors
 ```
 
-Download a compatible text encoder, video VAE and audio VAE from [FastH3 OmniRef Comfy](https://huggingface.co/FastVideo/FastH3-OmniRef-Comfy) and place them in `ComfyUI/models/text_encoders/` and `ComfyUI/models/vae/`. The audio VAE and the text encoder's reference-vision support are required. Select a text-encoder format supported by your GPU.
+Download a compatible text encoder, video VAE and audio VAE from [FastH3 Omni Comfy](https://huggingface.co/FastVideo/FastH3-OmniRef-Comfy) and place them in `ComfyUI/models/text_encoders/` and `ComfyUI/models/vae/`. The audio VAE and the text encoder's reference-vision support are required. Select a text-encoder format supported by your GPU.
 
 Accelerated NVFP4 inference requires NVIDIA Blackwell hardware. Use BF16 or FP8 on other GPU families. Quantized output can differ from BF16. This is the ComfyUI format; use the separate FastVideo-format model for FastVideo inference.
 
@@ -48,6 +48,12 @@ ComfyUI uses its own model layout, sampler and runtime kernels; outputs can diff
 - **UniServe — GB200/B200, RTX PRO 6000 Blackwell and Hopper:** use the [BF16 release](https://huggingface.co/FastVideo/FastVideo-FastH3-Omni-8-Step-V1) and [deployment guide](https://github.com/hao-ai-lab/uniserve/blob/main/docs/minimax_h3/minimax_h3.md).
 - **FastVideo local AI — DGX Spark and RTX 5090:** use the [FastVideo-format NVFP4 QAD model](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD) and [local inference guide](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/inference/fasth3_omniref.md).
 
+## Local AI resources
+
+Run FastH3 Omni on **DGX Spark or RTX 5090 through FastVideo** using the [FastVideo-format NVFP4 QAD weights](https://huggingface.co/FastVideo/FastH3-OmniRef-NVFP4-QAD). Start with the [FastVideo cookbook](https://haoailab.com/FastVideo/cookbook/) and [FastH3 Omni recipe builder](https://haoailab.com/FastVideo/cookbook/minimax-h3/fasth3-omniref/); use the [Spark recipe](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_spark.yaml) or [RTX 5090 recipe](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_rtx5090.yaml) and the [local inference guide](https://github.com/hao-ai-lab/FastVideo/blob/main/docs/inference/fasth3_omniref.md) for the AdaLN table, offload and decoder setup.
+
+[FP8 weights](https://huggingface.co/FastVideo/FastH3-OmniRef-FP8) are a separate FastVideo variant; the [FP8 recipe for RTX 4090](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_fasth3_omniref_rtx4090.yaml) illustrates the non-FP4 path with layerwise offload and compatible BF16 encoder components. Use each runtime's matching checkpoint format.
+
 ## License
 
 Use of these weights is governed by the [MiniMax-H3 Community License Agreement](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE).