[feat] Add MiniMax H3 (#1674)

docs/design/inference_schema_parity_inventory.yaml

@@ -445,7 +445,11 @@ surfaces:
     moved:
       image_path: request.inputs.image_path
       pil_image: request.inputs.pil_image
+      last_image: request.inputs.last_image
+      references: request.inputs.references
       video_path: request.inputs.video_path
+      latents: request.inputs.latents
+      audio_latents: request.inputs.audio_latents
       mouse_cond: request.inputs.mouse_cond
       keyboard_cond: request.inputs.keyboard_cond
       grid_sizes: request.inputs.grid_sizes
@@ -525,7 +529,6 @@ surfaces:
       inpaint_mask: request.extensions.stable_audio.inpaint_mask
     internal_only:
       data_type: "Derived from the request shape and not a public input."
-      latents: "Pre-generated diffusion latents supplied by parity/debug harnesses; not a public input."
 
   sampling_param_extensions: {}
 

docs/inference/support_matrix.md

@@ -66,6 +66,7 @@ column links a runnable script in `examples/inference/basic/` where one exists.
 | ltx2 | `Lightricks/LTX-2`<br>`FastVideo/LTX2-base`<br>`FastVideo/LTX2-Diffusers` | T2V | [basic_ltx2.py](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_ltx2.py) |
 | matrixgame | `FastVideo/Matrix-Game-2.0-Base-Distilled-Diffusers`<br>`FastVideo/Matrix-Game-2.0-GTA-Distilled-Diffusers`<br>`FastVideo/Matrix-Game-2.0-TempleRun-Distilled-Diffusers`<br>`FastVideo/Matrix-Game-2.0-Base-Diffusers`<br>`FastVideo/Matrix-Game-2.0-GTA-Diffusers`<br>`FastVideo/Matrix-Game-2.0-TempleRun-Diffusers`<br>`mignonjia/mg_longtuning_distilled_zelda`<br>`mignonjia/mg_sf_distilled_zelda_1k_steps`<br>`mignonjia/mg_sf_distilled_zelda`<br>`mignonjia/mg_causal_zelda`<br>`mignonjia/mg_bidirectional_zelda` | I2V | [basic_matrixgame2.py](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_matrixgame2.py) |
 | matrixgame | `FastVideo/Matrix-Game-3.0-Base-Distilled-Diffusers` | I2V | [basic_matrixgame3.py](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_matrixgame3.py) |
+| minimax_h3 | `MiniMaxAI/MiniMax-H3` | T2V, I2V | [T2VA](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_minimax_h3_t2v.py)<br>[FL2VA](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_minimax_h3_fl2va.py)<br>[Ref2VA](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_minimax_h3_ref2va.py) |
 | sd35 | `stabilityai/stable-diffusion-3.5-medium` | T2I | [basic_sd35_t2i.py](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_sd35_t2i.py) |
 | stable_audio | `FastVideo/stable-audio-open-1.0-Diffusers` | T2V | [basic_stable_audio.py](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_stable_audio.py) |
 | stable_audio | `FastVideo/stable-audio-open-small-Diffusers` | T2V | [basic_stable_audio_small.py](https://github.com/hao-ai-lab/FastVideo/blob/main/examples/inference/basic/basic_stable_audio_small.py) |
@@ -93,6 +94,10 @@ column links a runnable script in `examples/inference/basic/` where one exists.
 (`StableAudioT2AConfig` / `StableAudioOpenSmallConfig`); they are registered
 under the generic T2V workload option in the registry.
 
+**Note (MiniMax H3)**: T2VA, FL2VA, and Ref2VA all generate video with stereo
+audio. Use the Ref2VA example when passing ordered image, video, or audio
+references.
+
 **Note (Wan-VACE)**: not currently supported — no VACE pipeline or registered
 model ID exists on `main`
 ([#1435](https://github.com/hao-ai-lab/FastVideo/issues/1435)). The closest