feat(server): add recipe constraints and update generation workspace (#2217)

examples/server/recipes/README.md

@@ -77,3 +77,35 @@ These are built-in catalog rules. Users may keep personal presets in
 `<model-dir>/recipes/`; they need not add those presets to the built-in list.
 See [the recipe schema and feature reference](../api.md#user-recipe-format)
 for supported fields.
+
+## Output dimension alignment
+
+Set `size_multiple` when the runtime's output dimension alignment differs from
+the default of `8`. Match `GenerationRequest::align_image_size` in
+[`src/pipeline/request.cpp`](../../../src/pipeline/request.cpp): the VAE scale
+factor multiplied by the model definition's `diffusion_down_factor`. The scale
+comes from [`VAE::get_scale_factor`](../../../src/model/vae/vae.hpp), with the
+PiD override in [`diffusion_engine.cpp`](../../../src/pipeline/diffusion_engine.cpp);
+model geometry is defined under [`src/model/integrations`](../../../src/model/integrations/).
+
+Use the runtime's output alignment, not the nominal patch size: some models pad
+patches internally and crop their output back to the requested size. Pixel-space
+models with an alignment of `1` explicitly use `size_multiple: 1`. MiniT2I also
+has this alignment, but its separate fixed `512 × 512` output restriction still
+applies. Reference-image preprocessing constraints are independent of this field.
+
+## Video length constraints
+
+Video recipes declare `video_constraints` to match `align_video_frames` in
+[`diffusion_engine.cpp`](../../../src/pipeline/diffusion_engine.cpp) and the FPS
+and AnimateDiff overrides in
+[`request.cpp`](../../../src/pipeline/request.cpp). Wan, HunyuanVideo and LingBot
+round down to `4n + 1`; LTX rounds down to `8n + 1`. MiniMax-H3 rounds up to
+`17n + 5`, with at least 5 frames and fixed 24 FPS. AnimateDiff accepts whole
+frames up to 32. Wan 2.2 S2V fixes FPS at 16.
+
+Declare fixed FPS only where the runtime enforces it; recommended FPS belongs
+in `defaults.fps`. These constraints guide UI conversion and estimates, not
+runtime behavior. Audio-driven output and temporal upscaling may still change
+the final frame count. See the [recipe schema](../api.md#user-recipe-format)
+for field defaults and validation rules.

examples/server/recipes/animatediff-sd15.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "animatediff-sd15",
   "name": "AnimateDiff SD 1.5",
+  "size_multiple": 64,
   "description": "Use Video Generation with an SD 1.5 checkpoint and compatible motion module.",
   "model_url": "https://huggingface.co/guoyww/animatediff",
   "slots": [
@@ -22,6 +23,13 @@
       "required": false
     }
   ],
+  "video_constraints": {
+    "frame_step": 1,
+    "frame_offset": 0,
+    "frame_rounding": "floor",
+    "min_frames": 1,
+    "max_frames": 32
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 8,

examples/server/recipes/chroma-radiance.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "chroma-radiance",
   "name": "Chroma Radiance",
+  "size_multiple": 1,
   "description": "Pixel-space generation without a VAE. Also accepts the x0 and experimental patch-32 variants.",
   "model_url": "https://huggingface.co/lodestones/Chroma1-Radiance",
   "slots": [

examples/server/recipes/cosxl-edit.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "cosxl-edit",
   "name": "CosXL Edit",
+  "size_multiple": 64,
   "description": "Supply the image to edit as a reference image.",
   "model_url": "https://huggingface.co/stabilityai/cosxl",
   "slots": [

examples/server/recipes/ernie-image-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ernie-image-turbo",
   "name": "ERNIE Image Turbo",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/baidu/ERNIE-Image-Turbo",
   "slots": [
     {

examples/server/recipes/ernie-image.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ernie-image",
   "name": "ERNIE Image",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/baidu/ERNIE-Image",
   "slots": [
     {

examples/server/recipes/fibo2-dev.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "fibo2-dev",
   "name": "Fibo 2.0 Dev",
+  "size_multiple": 16,
   "description": "Text-to-image generation and native reference-image editing. Select a separate vision projector for editing when it is not bundled in the text encoder.",
   "model_url": "https://huggingface.co/briaai/Fibo-2.0-dev",
   "slots": [

examples/server/recipes/fibo2-edit-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "fibo2-edit-turbo",
   "name": "Fibo 2.0 Edit Turbo",
+  "size_multiple": 16,
   "description": "Dedicated reference-image editing checkpoint; supply reference images. Select a separate vision projector when it is not bundled in the text encoder.",
   "model_url": "https://huggingface.co/briaai/Fibo-2.0-edit-turbo",
   "slots": [

examples/server/recipes/flux2-dev.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux2-dev",
   "name": "FLUX.2 dev",
+  "size_multiple": 16,
   "description": "Supports text-to-image and reference-image editing.",
   "model_url": "https://huggingface.co/black-forest-labs/FLUX.2-dev",
   "slots": [

examples/server/recipes/flux2-klein-4b.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux2-klein-4b",
   "name": "FLUX.2 Klein 4B",
+  "size_multiple": 16,
   "description": "Supports reference-image editing. The FLUX.2 small decoder is an alternative VAE.",
   "model_url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-4B",
   "slots": [

examples/server/recipes/flux2-klein-9b.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux2-klein-9b",
   "name": "FLUX.2 Klein 9B",
+  "size_multiple": 16,
   "description": "Supports text-to-image and reference-image editing.",
   "model_url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-9B",
   "slots": [

examples/server/recipes/flux2-klein-base-4b.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux2-klein-base-4b",
   "name": "FLUX.2 Klein Base 4B",
+  "size_multiple": 16,
   "description": "Supports text-to-image and reference-image editing.",
   "model_url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B",
   "slots": [

examples/server/recipes/flux2-klein-base-9b.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux2-klein-base-9b",
   "name": "FLUX.2 Klein Base 9B",
+  "size_multiple": 16,
   "description": "Use the 9B base transformer with Qwen 3 8B. Supports reference-image editing.",
   "model_url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B",
   "slots": [

examples/server/recipes/flux3-klein-base.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux3-klein-base",
   "name": "FLUX.3 Image Klein Base",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/black-forest-labs/flux-3-image-klein-base",
   "slots": [
     {

examples/server/recipes/flux3-klein.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "flux3-klein",
   "name": "FLUX.3 Image Klein",
+  "size_multiple": 16,
   "description": "Supports text-to-image and reference-image editing.",
   "model_url": "https://huggingface.co/black-forest-labs/flux-3-image-klein",
   "slots": [

examples/server/recipes/hidream-o1-dev.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "hidream-o1-dev",
   "name": "HiDream O1 Image dev",
+  "size_multiple": 1,
   "description": "Bundled checkpoint; also supports reference-image editing.",
   "model_url": "https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev",
   "slots": [

examples/server/recipes/hunyuan-video-15-i2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "hunyuan-video-15-i2v",
   "name": "HunyuanVideo 1.5 I2V",
+  "size_multiple": 16,
   "description": "Select HunyuanVideo 1.5 I2V weights and supply a start image in Video Generation.",
   "model_url": "https://huggingface.co/tencent/HunyuanVideo-1.5",
   "slots": [
@@ -36,6 +37,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/hunyuan-video-15-t2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "hunyuan-video-15-t2v",
   "name": "HunyuanVideo 1.5 T2V",
+  "size_multiple": 16,
   "description": "Select HunyuanVideo 1.5 T2V weights and use Video Generation. Use the separate I2V recipe for I2V weights.",
   "model_url": "https://huggingface.co/tencent/HunyuanVideo-1.5",
   "slots": [
@@ -36,6 +37,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/ideogram4.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ideogram4",
   "name": "Ideogram 4",
+  "size_multiple": 16,
   "description": "Select the matching unconditional transformer for classifier-free guidance.",
   "model_url": "https://huggingface.co/ideogram-ai/ideogram-4-fp8",
   "slots": [

examples/server/recipes/instruct-pix2pix.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "instruct-pix2pix",
   "name": "Instruct-Pix2Pix",
+  "size_multiple": 64,
   "description": "Supply the image to edit as a reference image.",
   "model_url": "https://huggingface.co/timbrooks/instruct-pix2pix",
   "slots": [

examples/server/recipes/iris-3b.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "iris-3b",
   "name": "Iris 3B",
+  "size_multiple": 16,
   "description": "Pixel-space model; no VAE is required.",
   "model_url": "https://huggingface.co/speridlabs/iris-3b",
   "slots": [

examples/server/recipes/lens-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "lens-turbo",
   "name": "LENS Turbo",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/microsoft/Lens-Turbo",
   "slots": [
     {

examples/server/recipes/lens.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "lens",
   "name": "LENS",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/microsoft/Lens",
   "slots": [
     {

examples/server/recipes/lingbot-video-dense.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "lingbot-video-dense",
   "name": "LingBot Video Dense 1.3B",
+  "size_multiple": 16,
   "description": "Use Video Generation.",
   "model_url": "https://huggingface.co/robbyant/lingbot-video-dense-1.3b",
   "slots": [
@@ -30,6 +31,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "video_frames": 33,
     "cfg_scale": 3,

examples/server/recipes/lingbot-video-moe.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "lingbot-video-moe",
   "name": "LingBot Video MoE 30B A3B",
+  "size_multiple": 16,
   "description": "Use Video Generation.",
   "model_url": "https://huggingface.co/robbyant/lingbot-video-moe-30b-a3b",
   "slots": [
@@ -30,6 +31,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "video_frames": 33,
     "cfg_scale": 3,

examples/server/recipes/llada-image-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "llada-image-turbo",
   "name": "LLaDA Image Turbo",
+  "size_multiple": 16,
   "description": "Use matching turbo text encoder and connectors. Editing needs connectors that include the SigVQ encoder.",
   "model_url": "https://huggingface.co/inclusionAI/LLaDA-Image-Turbo",
   "slots": [

examples/server/recipes/llada-image.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "llada-image",
   "name": "LLaDA Image (base)",
+  "size_multiple": 16,
   "description": "Use matching base transformer, text encoder and connectors; do not mix them with Turbo components. Editing needs connectors with SigVQ and 1024x1024 output.",
   "model_url": "https://huggingface.co/inclusionAI/LLaDA-Image",
   "slots": [

examples/server/recipes/ltx23-dev.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ltx23-dev",
   "name": "LTX 2.3 dev",
+  "size_multiple": 32,
   "description": "Supports text, start-image and start/end-image video. Audio VAE is optional for silent video. Configure latent upscaling separately in generation settings. Optional distillation LoRAs use this recipe; select the LoRA and adjust the sampling settings separately.",
   "model_url": "https://huggingface.co/Lightricks/LTX-2.3",
   "slots": [
@@ -39,6 +40,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 8,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/ltx23-distilled.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ltx23-distilled",
   "name": "LTX 2.3 Distilled 1.1",
+  "size_multiple": 32,
   "description": "Supports text, start-image and start/end-image video. Audio VAE is optional for silent video. Configure latent upscaling separately in generation settings.",
   "model_url": "https://huggingface.co/Lightricks/LTX-2.3",
   "slots": [
@@ -39,6 +40,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 8,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 121,

examples/server/recipes/ltx25-dev.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ltx25-dev",
   "name": "LTX 2.5 dev",
+  "size_multiple": 32,
   "description": "Use the conv video VAE and LTX-specific Gemma 4 with bundled projection. Audio VAE is optional for silent video.",
   "model_url": "https://huggingface.co/Lightricks/LTX-2.5",
   "slots": [
@@ -35,6 +36,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 8,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "fps": 24,

examples/server/recipes/mage-flow-edit.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "mage-flow-edit",
   "name": "Mage Flow Edit",
+  "size_multiple": 16,
   "description": "Supply reference images. Select a separate vision projector when it is not bundled in the text encoder.",
   "model_url": "https://huggingface.co/microsoft/Mage-Flow-Edit",
   "slots": [

examples/server/recipes/mage-flow-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "mage-flow-turbo",
   "name": "Mage Flow Turbo",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/microsoft/Mage-Flow-Turbo",
   "slots": [
     {

examples/server/recipes/mage-flow.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "mage-flow",
   "name": "Mage Flow",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/microsoft/Mage-Flow",
   "slots": [
     {

examples/server/recipes/ming-image.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "ming-image",
   "name": "Ming Image 0.1",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/inclusionAI/Ming-Image-0.1-Design",
   "slots": [
     {

examples/server/recipes/minimax-h3-fl2va.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "minimax-h3-fl2va",
   "name": "MiniMax H3 FL2VA",
+  "size_multiple": 32,
   "description": "Generate video and audio, optionally with start/end images. Supports full and pruned FL2VA weights. Audio VAE is optional for silent video.",
   "model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3",
   "slots": [
@@ -35,6 +36,13 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 17,
+    "frame_offset": 5,
+    "frame_rounding": "ceil",
+    "min_frames": 5,
+    "fixed_fps": 24
+  },
   "defaults": {
     "video_frames": 56,
     "fps": 24,

examples/server/recipes/minimax-h3-ref2va.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "minimax-h3-ref2va",
   "name": "MiniMax H3 Ref2VA",
+  "size_multiple": 32,
   "description": "Supply image, video or audio references with compatible Ref2VA weights. Audio VAE is optional for silent video.",
   "model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3",
   "slots": [
@@ -35,6 +36,13 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 17,
+    "frame_offset": 5,
+    "frame_rounding": "ceil",
+    "min_frames": 5,
+    "fixed_fps": 24
+  },
   "defaults": {
     "video_frames": 56,
     "fps": 24,

examples/server/recipes/minit2i.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "minit2i",
   "name": "MiniT2I",
+  "size_multiple": 1,
   "description": "Pixel-space model; no VAE is required.",
   "model_url": "https://huggingface.co/MiniT2I/MiniT2I",
   "slots": [

examples/server/recipes/moss-image-base.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "moss-image-base",
   "name": "MOSS Image Base",
+  "size_multiple": 16,
   "description": "Select the MOSS-Image-Base transformer with its matching text encoder and FLUX.2 VAE or TAE.",
   "model_url": "https://huggingface.co/OpenMOSS-Team/MOSS-Image-Base",
   "slots": [

examples/server/recipes/moss-image-sft.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "moss-image-sft",
   "name": "MOSS Image SFT",
+  "size_multiple": 16,
   "description": "Select the MOSS-Image-SFT transformer with its matching text encoder and FLUX.2 VAE or TAE.",
   "model_url": "https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT",
   "slots": [

examples/server/recipes/nitrosd-realism.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "nitrosd-realism",
   "name": "NitroSD Realism",
+  "size_multiple": 64,
   "model_url": "https://huggingface.co/ChenDY/NitroFusion",
   "slots": [
     {

examples/server/recipes/pid-15-flux2.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-15-flux2",
   "name": "PiD 1.5 (Flux.2 VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a matching Flux.2 PiD checkpoint and VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid-15-qwen-image.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-15-qwen-image",
   "name": "PiD 1.5 (Qwen Image VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a matching Qwen Image PiD checkpoint and VAE. Use the Qwen Image 2D VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid-15-sd3.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-15-sd3",
   "name": "PiD 1.5 (SD3 VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a matching SD3 PiD checkpoint and VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid-15.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-15",
   "name": "PiD 1.5 (Flux / Z-Image VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a Flux/Z-Image PiD checkpoint and matching Flux VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid-flux2.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-flux2",
   "name": "PiD (Flux.2 VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a matching Flux.2 PiD checkpoint and VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid-qwen-image.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-qwen-image",
   "name": "PiD (Qwen Image VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a matching Qwen Image PiD checkpoint and VAE. Use the Qwen Image 2D VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid-sd3.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid-sd3",
   "name": "PiD (SD3 VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a matching SD3 PiD checkpoint and VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pid.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pid",
   "name": "PiD (Flux / Z-Image VAE)",
+  "size_multiple": 1,
   "description": "Supply a reference image; the first image is used as the source latent. Select a Flux/Z-Image PiD checkpoint and matching Flux VAE.",
   "model_url": "https://huggingface.co/nvidia/PiD",
   "slots": [

examples/server/recipes/pixart-alpha-1024.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pixart-alpha-1024",
   "name": "PixArt Alpha XL 1024",
+  "size_multiple": 16,
   "description": "Use the matching PixArt Alpha transformer and SD 1.x-style VAE. Resolution/aspect-ratio micro-conditioning is not currently applied by the runtime.",
   "model_url": "https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS",
   "slots": [

examples/server/recipes/pixart-alpha-512.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pixart-alpha-512",
   "name": "PixArt Alpha XL 512",
+  "size_multiple": 16,
   "description": "Use the matching PixArt Alpha transformer and SD 1.x-style VAE. Resolution/aspect-ratio micro-conditioning is not currently applied by the runtime.",
   "model_url": "https://huggingface.co/PixArt-alpha/PixArt-XL-2-512x512",
   "slots": [

examples/server/recipes/pixart-sigma.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "pixart-sigma",
   "name": "PixArt Sigma XL 1024",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
   "slots": [
     {

examples/server/recipes/qwen-image-21-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "qwen-image-21-turbo",
   "name": "Qwen Image 2.1 Turbo",
+  "size_multiple": 32,
   "description": "Use the standalone Turbo diffusion weights for generation and editing with the fixed 8-step schedule. Select the Qwen Image 2.1 VAE or TAEQI2.1, and supply a vision projector when needed.",
   "model_url": "https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo",
   "slots": [

examples/server/recipes/qwen-image-21.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "qwen-image-21",
   "name": "Qwen Image 2.1",
+  "size_multiple": 32,
   "description": "Supports generation and editing. Select the full Qwen Image 2.1 VAE or TAEQI2.1. Supply a separate vision projector when needed. Select acceleration LoRAs and adjust their settings separately.",
   "model_url": "https://huggingface.co/Qwen/Qwen-Image-2.1",
   "slots": [

examples/server/recipes/sd-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd-turbo",
   "name": "SD Turbo",
+  "size_multiple": 64,
   "description": "Select a single-file SD-Turbo checkpoint. Uses one step with CFG disabled (scale 1 in sd.cpp); use more steps for partial image-to-image denoising.",
   "model_url": "https://huggingface.co/stabilityai/sd-turbo",
   "slots": [

examples/server/recipes/sd1-checkpoint.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd1-checkpoint",
   "name": "SD 1.x",
+  "size_multiple": 64,
   "description": "Supports SD 1.x, compatible LCM checkpoints and layer-count variants. For LCM weights, select LCM sampling and adjust steps/CFG. Tiny SD Diffusers directories must first be converted into a single-file checkpoint.",
   "model_url": "https://huggingface.co/CompVis/stable-diffusion-v1-4",
   "slots": [

examples/server/recipes/sd1-controlnet.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd1-controlnet",
   "name": "SD 1.5 ControlNet",
+  "size_multiple": 64,
   "description": "Supply a control image; input image and mask are optional for image-to-image or inpainting.",
   "model_url": "https://huggingface.co/lllyasviel/control_v11p_sd15_canny",
   "slots": [

examples/server/recipes/sd1-inpainting.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd1-inpainting",
   "name": "SD 1.5 Inpainting",
+  "size_multiple": 64,
   "description": "Select an inpainting checkpoint, then supply an input image and mask.",
   "slots": [
     {

examples/server/recipes/sd1-ip-adapter.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd1-ip-adapter",
   "name": "SD 1.5 IP-Adapter / Plus",
+  "size_multiple": 64,
   "description": "Select matching SD 1.5 IP-Adapter or Plus weights and CLIP Vision H, then supply an IP-Adapter image.",
   "model_url": "https://huggingface.co/h94/IP-Adapter",
   "slots": [

examples/server/recipes/sd2-512-checkpoint.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd2-512-checkpoint",
   "name": "SD 2.1 512",
+  "size_multiple": 64,
   "description": "Supports SD 2.x 512 and compatible layer-count variants. Tiny SD2 Diffusers directories must first be converted into a single-file checkpoint.",
   "slots": [
     {

examples/server/recipes/sd2-768-checkpoint.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd2-768-checkpoint",
   "name": "SD 2.1 768",
+  "size_multiple": 64,
   "slots": [
     {
       "id": "model",

examples/server/recipes/sd2-inpainting.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sd2-inpainting",
   "name": "SD 2 Inpainting",
+  "size_multiple": 64,
   "description": "Select an inpainting checkpoint, then supply Init Image and Mask Image.",
   "slots": [
     {

examples/server/recipes/sdxl-checkpoint.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxl-checkpoint",
   "name": "SDXL",
+  "size_multiple": 64,
   "description": "Supports SDXL and compatible reduced-depth checkpoints such as SSD-1B and Segmind Vega.",
   "model_url": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0",
   "slots": [

examples/server/recipes/sdxl-controlnet.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxl-controlnet",
   "name": "SDXL ControlNet",
+  "size_multiple": 64,
   "description": "Select a compatible SDXL ControlNet and supply a preprocessed control image. Input image and mask are optional for image-to-image or inpainting.",
   "model_url": "https://huggingface.co/diffusers/controlnet-canny-sdxl-1.0",
   "slots": [

examples/server/recipes/sdxl-inpainting.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxl-inpainting",
   "name": "SDXL Inpainting",
+  "size_multiple": 64,
   "description": "Select an inpainting checkpoint, then supply Init Image and Mask Image.",
   "model_url": "https://huggingface.co/diffusers/stable-diffusion-xl-1.0-inpainting-0.1",
   "slots": [

examples/server/recipes/sdxl-ip-adapter.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxl-ip-adapter",
   "name": "SDXL IP-Adapter / Plus",
+  "size_multiple": 64,
   "description": "Select matching SDXL ViT-H IP-Adapter or Plus weights and CLIP Vision H, then supply an IP-Adapter image.",
   "model_url": "https://huggingface.co/h94/IP-Adapter",
   "slots": [

examples/server/recipes/sdxl-photomaker.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxl-photomaker",
   "name": "SDXL PhotoMaker",
+  "size_multiple": 64,
   "description": "Select PhotoMaker v1 and supply identity images. Include the img trigger in the prompt.",
   "model_url": "https://huggingface.co/TencentARC/PhotoMaker",
   "slots": [

examples/server/recipes/sdxl-turbo.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxl-turbo",
   "name": "SDXL Turbo",
+  "size_multiple": 64,
   "model_url": "https://huggingface.co/stabilityai/sdxl-turbo",
   "slots": [
     {

examples/server/recipes/sdxs.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sdxs",
   "name": "SDXS",
+  "size_multiple": 64,
   "model_url": "https://huggingface.co/IDKiro/sdxs-512-dreamshaper",
   "slots": [
     {

examples/server/recipes/sefi-image.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sefi-image",
   "name": "SeFi Image 5B RL",
+  "size_multiple": 16,
   "model_url": "https://huggingface.co/SeFi-Image/SeFi-Image-5B-Base",
   "slots": [
     {

examples/server/recipes/sensenova-u15.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "sensenova-u15",
   "name": "SenseNova U1.5",
+  "size_multiple": 32,
   "description": "Bundled MoT checkpoint.",
   "model_url": "https://huggingface.co/sensenova/SenseNova-U1.5-8B-MoT",
   "slots": [

examples/server/recipes/wan21-flf2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan21-flf2v",
   "name": "Wan 2.1 FLF2V 14B",
+  "size_multiple": 16,
   "description": "Select FLF2V weights and supply both start and end images.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.1-FLF2V-14B-720P",
   "slots": [
@@ -35,6 +36,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "flow_shift": 16,

examples/server/recipes/wan21-i2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan21-i2v",
   "name": "Wan 2.1 I2V",
+  "size_multiple": 16,
   "description": "Image-to-video with Wan 2.1, compatible SkyReels V2 weights, or a single Wan 2.2 I2V expert. CLIP Vision is required by Wan 2.1 I2V and is unused by Wan 2.2. Defaults target Wan 2.1 480p.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-480P",
   "slots": [
@@ -35,6 +36,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/wan21-t2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan21-t2v",
   "name": "Wan 2.1 T2V",
+  "size_multiple": 16,
   "description": "Text-to-video with Wan 2.1 or a compatible single Wan 2.2 T2V expert. Defaults target Wan 2.1 14B; adjust settings for the selected weights and acceleration LoRAs.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.1-T2V-14B",
   "slots": [
@@ -30,6 +31,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/wan21-vace.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan21-vace",
   "name": "Wan 2.1 VACE 1.3B / 14B",
+  "size_multiple": 16,
   "description": "Select matching VACE weights. Supports text, reference images and control video through Video Generation.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.1-VACE-14B",
   "slots": [
@@ -30,6 +31,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/wan22-i2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan22-i2v",
   "name": "Wan 2.2 I2V A14B",
+  "size_multiple": 16,
   "description": "Image-to-video. Select a start image in Video Generation after loading. LightX2V acceleration LoRAs must match the I2V low- and high-noise models; configure LoRAs and sampling separately.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B",
   "slots": [
@@ -35,6 +36,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/wan22-s2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan22-s2v",
   "name": "Wan 2.2 S2V 14B",
+  "size_multiple": 16,
   "description": "Supply a start image and reference audio through Video Generation.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.2-S2V-14B",
   "slots": [
@@ -35,6 +36,13 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1,
+    "fixed_fps": 16
+  },
   "defaults": {
     "sampling_method": "euler",
     "flow_shift": 3,

examples/server/recipes/wan22-t2v.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan22-t2v",
   "name": "Wan 2.2 T2V A14B",
+  "size_multiple": 16,
   "description": "Text-to-video. Use Video Generation after loading. LightX2V acceleration LoRAs must match the T2V low- and high-noise models; configure LoRAs and sampling separately.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B",
   "slots": [
@@ -35,6 +36,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/wan22-ti2v-5b.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "wan22-ti2v-5b",
   "name": "Wan 2.2 TI2V 5B",
+  "size_multiple": 32,
   "description": "Use Wan 2.2 VAE. Supports text, start-image and start/end-image conditioning.",
   "model_url": "https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B",
   "slots": [
@@ -30,6 +31,12 @@
       "tae"
     ]
   ],
+  "video_constraints": {
+    "frame_step": 4,
+    "frame_offset": 1,
+    "frame_rounding": "floor",
+    "min_frames": 1
+  },
   "defaults": {
     "sampling_method": "euler",
     "video_frames": 33,

examples/server/recipes/z-image-l2p.json

@@ -2,6 +2,7 @@
   "schema_version": 1,
   "id": "z-image-l2p",
   "name": "Z-Image L2P",
+  "size_multiple": 16,
   "description": "Pixel-space L2P checkpoint with Qwen 3 4B; no VAE is needed. Use dimensions divisible by 16.",
   "model_url": "https://huggingface.co/zhen-nan/L2P",
   "slots": [