Disable image model cards temporarily (#1247)

## Motivation

Image generation feature is not stable and causing issues for users.

Fixes #1242

## Changes

- Commented out image model cards (flux1-schnell, flux1-dev, qwen-image,
qwen-image-edit-2509) in `src/exo/shared/models/model_cards.py`
- Added reference to issue #1242 in the comment explaining why they are
disabled

## Why It Works

By commenting out the model cards, these image models will no longer
appear in the model list, preventing users from attempting to use the
unstable feature until it is stabilized.

## Test Plan

### Manual Testing
- Run exo and verify image models no longer appear in the model list

### Automated Testing
- No changes to automated tests needed - this simply removes models from
the available list

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

README.md

@@ -364,7 +364,7 @@ The `exo-bench` tool measures model prefill and token generation speed across di
 
 ```bash
 uv run bench/exo_bench.py \
-  --model llama-3.2-1b \
+  --model Llama-3.2-1B-Instruct-4bit \
   --pp 128,256,512 \
   --tg 128,256
 ```
@@ -385,7 +385,7 @@ uv run bench/exo_bench.py \
 
 ```bash
 uv run bench/exo_bench.py \
-  --model llama-3.2-1b \
+  --model Llama-3.2-1B-Instruct-4bit \
   --pp 128,512 \
   --tg 128 \
   --max-nodes 2 \

bench/exo_bench.py

@@ -195,14 +195,14 @@ def resolve_model_short_id(client: ExoClient, model_arg: str) -> tuple[str, str]
     data = models.get("data") or []
 
     for m in data:
-        if m.get("id") == model_arg:
-            short_id = str(m["id"])
-            full_id = str(m.get("hugging_face_id") or m["id"])
+        if m.get("name").lower() == model_arg.lower():
+            short_id = str(m["name"])
+            full_id = str(m.get("hugging_face_id") or m["name"])
             return short_id, full_id
 
     for m in data:
         if m.get("hugging_face_id") == model_arg:
-            short_id = str(m["id"])
+            short_id = str(m["name"])
             full_id = str(m["hugging_face_id"])
             return short_id, full_id
 
@@ -373,7 +373,7 @@ def main() -> int:
     short_id, full_model_id = resolve_model_short_id(client, args.model)
 
     previews_resp = client.request_json(
-        "GET", "/instance/previews", params={"model_id": short_id}
+        "GET", "/instance/previews", params={"model_id": full_model_id}
     )
     previews = previews_resp.get("previews") or []
 

dashboard/src/routes/downloads/+page.svelte

@@ -172,6 +172,33 @@
   }
 
   let downloadOverview = $state<NodeEntry[]>([]);
+  let models = $state<Array<{ id: string; storage_size_megabytes?: number }>>(
+    [],
+  );
+
+  async function fetchModels() {
+    try {
+      const response = await fetch("/models");
+      if (response.ok) {
+        const data = await response.json();
+        models = data.data || [];
+      }
+    } catch (error) {
+      console.error("Failed to fetch models:", error);
+    }
+  }
+
+  function getModelTotalBytes(
+    modelId: string,
+    downloadTotalBytes: number,
+  ): number {
+    if (downloadTotalBytes > 0) return downloadTotalBytes;
+    const model = models.find((m) => m.id === modelId);
+    if (model?.storage_size_megabytes) {
+      return model.storage_size_megabytes * 1024 * 1024;
+    }
+    return 0;
+  }
 
   $effect(() => {
     try {
@@ -346,6 +373,7 @@
   onMount(() => {
     // Ensure we fetch at least once when visiting downloads directly
     refreshState();
+    fetchModels();
   });
 </script>
 
@@ -454,7 +482,7 @@
                     {#if model.status !== "completed"}
                       <div class="text-[11px] text-exo-light-gray font-mono">
                         {formatBytes(model.downloadedBytes)} / {formatBytes(
-                          model.totalBytes,
+                          getModelTotalBytes(model.modelId, model.totalBytes),
                         )}
                       </div>
                     {/if}

src/exo/shared/models/model_cards.py

@@ -59,8 +59,9 @@ class ModelCard(CamelCaseModel):
 
     @staticmethod
     async def load(model_id: ModelId) -> "ModelCard":
-        if model_id in MODEL_CARDS:
-            return MODEL_CARDS[model_id]
+        for card in MODEL_CARDS.values():
+            if card.model_id == model_id:
+                return card
         return await ModelCard.from_hf(model_id)
 
     @staticmethod
@@ -409,158 +410,159 @@ MODEL_CARDS: dict[str, ModelCard] = {
         supports_tensor=True,
         tasks=[ModelTask.TextGeneration],
     ),
-    "flux1-schnell": ModelCard(
-        model_id=ModelId("black-forest-labs/FLUX.1-schnell"),
-        storage_size=Memory.from_bytes(23782357120 + 9524621312),
-        n_layers=57,
-        hidden_size=1,
-        supports_tensor=False,
-        tasks=[ModelTask.TextToImage],
-        components=[
-            ComponentInfo(
-                component_name="text_encoder",
-                component_path="text_encoder/",
-                storage_size=Memory.from_kb(0),
-                n_layers=12,
-                can_shard=False,
-                safetensors_index_filename=None,  # Single file
-            ),
-            ComponentInfo(
-                component_name="text_encoder_2",
-                component_path="text_encoder_2/",
-                storage_size=Memory.from_bytes(9524621312),
-                n_layers=24,
-                can_shard=False,
-                safetensors_index_filename="model.safetensors.index.json",
-            ),
-            ComponentInfo(
-                component_name="transformer",
-                component_path="transformer/",
-                storage_size=Memory.from_bytes(23782357120),
-                n_layers=57,  # 19 transformer_blocks + 38 single_transformer_blocks
-                can_shard=True,
-                safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
-            ),
-            ComponentInfo(
-                component_name="vae",
-                component_path="vae/",
-                storage_size=Memory.from_kb(0),
-                n_layers=None,
-                can_shard=False,
-                safetensors_index_filename=None,
-            ),
-        ],
-    ),
-    "flux1-dev": ModelCard(
-        model_id=ModelId("black-forest-labs/FLUX.1-dev"),
-        storage_size=Memory.from_bytes(23782357120 + 9524621312),
-        n_layers=57,
-        hidden_size=1,
-        supports_tensor=False,
-        tasks=[ModelTask.TextToImage, ModelTask.ImageToImage],
-        components=[
-            ComponentInfo(
-                component_name="text_encoder",
-                component_path="text_encoder/",
-                storage_size=Memory.from_kb(0),
-                n_layers=12,
-                can_shard=False,
-                safetensors_index_filename=None,  # Single file
-            ),
-            ComponentInfo(
-                component_name="text_encoder_2",
-                component_path="text_encoder_2/",
-                storage_size=Memory.from_bytes(9524621312),
-                n_layers=24,
-                can_shard=False,
-                safetensors_index_filename="model.safetensors.index.json",
-            ),
-            ComponentInfo(
-                component_name="transformer",
-                component_path="transformer/",
-                storage_size=Memory.from_bytes(23802816640),
-                n_layers=57,  # 19 transformer_blocks + 38 single_transformer_blocks
-                can_shard=True,
-                safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
-            ),
-            ComponentInfo(
-                component_name="vae",
-                component_path="vae/",
-                storage_size=Memory.from_kb(0),
-                n_layers=None,
-                can_shard=False,
-                safetensors_index_filename=None,
-            ),
-        ],
-    ),
-    "qwen-image": ModelCard(
-        model_id=ModelId("Qwen/Qwen-Image"),
-        storage_size=Memory.from_bytes(16584333312 + 40860802176),
-        n_layers=60,  # Qwen has 60 transformer blocks (all joint-style)
-        hidden_size=1,
-        supports_tensor=False,
-        tasks=[ModelTask.TextToImage, ModelTask.ImageToImage],
-        components=[
-            ComponentInfo(
-                component_name="text_encoder",
-                component_path="text_encoder/",
-                storage_size=Memory.from_kb(16584333312),
-                n_layers=12,
-                can_shard=False,
-                safetensors_index_filename=None,  # Single file
-            ),
-            ComponentInfo(
-                component_name="transformer",
-                component_path="transformer/",
-                storage_size=Memory.from_bytes(40860802176),
-                n_layers=60,
-                can_shard=True,
-                safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
-            ),
-            ComponentInfo(
-                component_name="vae",
-                component_path="vae/",
-                storage_size=Memory.from_kb(0),
-                n_layers=None,
-                can_shard=False,
-                safetensors_index_filename=None,
-            ),
-        ],
-    ),
-    "qwen-image-edit-2509": ModelCard(
-        model_id=ModelId("Qwen/Qwen-Image-Edit-2509"),
-        storage_size=Memory.from_bytes(16584333312 + 40860802176),
-        n_layers=60,  # Qwen has 60 transformer blocks (all joint-style)
-        hidden_size=1,
-        supports_tensor=False,
-        tasks=[ModelTask.ImageToImage],
-        components=[
-            ComponentInfo(
-                component_name="text_encoder",
-                component_path="text_encoder/",
-                storage_size=Memory.from_kb(16584333312),
-                n_layers=12,
-                can_shard=False,
-                safetensors_index_filename=None,  # Single file
-            ),
-            ComponentInfo(
-                component_name="transformer",
-                component_path="transformer/",
-                storage_size=Memory.from_bytes(40860802176),
-                n_layers=60,
-                can_shard=True,
-                safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
-            ),
-            ComponentInfo(
-                component_name="vae",
-                component_path="vae/",
-                storage_size=Memory.from_kb(0),
-                n_layers=None,
-                can_shard=False,
-                safetensors_index_filename=None,
-            ),
-        ],
-    ),
+    # Image models commented out - feature not stable (see https://github.com/exo-explore/exo/issues/1242)
+    # "flux1-schnell": ModelCard(
+    #     model_id=ModelId("black-forest-labs/FLUX.1-schnell"),
+    #     storage_size=Memory.from_bytes(23782357120 + 9524621312),
+    #     n_layers=57,
+    #     hidden_size=1,
+    #     supports_tensor=False,
+    #     tasks=[ModelTask.TextToImage],
+    #     components=[
+    #         ComponentInfo(
+    #             component_name="text_encoder",
+    #             component_path="text_encoder/",
+    #             storage_size=Memory.from_kb(0),
+    #             n_layers=12,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,  # Single file
+    #         ),
+    #         ComponentInfo(
+    #             component_name="text_encoder_2",
+    #             component_path="text_encoder_2/",
+    #             storage_size=Memory.from_bytes(9524621312),
+    #             n_layers=24,
+    #             can_shard=False,
+    #             safetensors_index_filename="model.safetensors.index.json",
+    #         ),
+    #         ComponentInfo(
+    #             component_name="transformer",
+    #             component_path="transformer/",
+    #             storage_size=Memory.from_bytes(23782357120),
+    #             n_layers=57,  # 19 transformer_blocks + 38 single_transformer_blocks
+    #             can_shard=True,
+    #             safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
+    #         ),
+    #         ComponentInfo(
+    #             component_name="vae",
+    #             component_path="vae/",
+    #             storage_size=Memory.from_kb(0),
+    #             n_layers=None,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,
+    #         ),
+    #     ],
+    # ),
+    # "flux1-dev": ModelCard(
+    #     model_id=ModelId("black-forest-labs/FLUX.1-dev"),
+    #     storage_size=Memory.from_bytes(23782357120 + 9524621312),
+    #     n_layers=57,
+    #     hidden_size=1,
+    #     supports_tensor=False,
+    #     tasks=[ModelTask.TextToImage, ModelTask.ImageToImage],
+    #     components=[
+    #         ComponentInfo(
+    #             component_name="text_encoder",
+    #             component_path="text_encoder/",
+    #             storage_size=Memory.from_kb(0),
+    #             n_layers=12,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,  # Single file
+    #         ),
+    #         ComponentInfo(
+    #             component_name="text_encoder_2",
+    #             component_path="text_encoder_2/",
+    #             storage_size=Memory.from_bytes(9524621312),
+    #             n_layers=24,
+    #             can_shard=False,
+    #             safetensors_index_filename="model.safetensors.index.json",
+    #         ),
+    #         ComponentInfo(
+    #             component_name="transformer",
+    #             component_path="transformer/",
+    #             storage_size=Memory.from_bytes(23802816640),
+    #             n_layers=57,  # 19 transformer_blocks + 38 single_transformer_blocks
+    #             can_shard=True,
+    #             safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
+    #         ),
+    #         ComponentInfo(
+    #             component_name="vae",
+    #             component_path="vae/",
+    #             storage_size=Memory.from_kb(0),
+    #             n_layers=None,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,
+    #         ),
+    #     ],
+    # ),
+    # "qwen-image": ModelCard(
+    #     model_id=ModelId("Qwen/Qwen-Image"),
+    #     storage_size=Memory.from_bytes(16584333312 + 40860802176),
+    #     n_layers=60,  # Qwen has 60 transformer blocks (all joint-style)
+    #     hidden_size=1,
+    #     supports_tensor=False,
+    #     tasks=[ModelTask.TextToImage, ModelTask.ImageToImage],
+    #     components=[
+    #         ComponentInfo(
+    #             component_name="text_encoder",
+    #             component_path="text_encoder/",
+    #             storage_size=Memory.from_kb(16584333312),
+    #             n_layers=12,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,  # Single file
+    #         ),
+    #         ComponentInfo(
+    #             component_name="transformer",
+    #             component_path="transformer/",
+    #             storage_size=Memory.from_bytes(40860802176),
+    #             n_layers=60,
+    #             can_shard=True,
+    #             safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
+    #         ),
+    #         ComponentInfo(
+    #             component_name="vae",
+    #             component_path="vae/",
+    #             storage_size=Memory.from_kb(0),
+    #             n_layers=None,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,
+    #         ),
+    #     ],
+    # ),
+    # "qwen-image-edit-2509": ModelCard(
+    #     model_id=ModelId("Qwen/Qwen-Image-Edit-2509"),
+    #     storage_size=Memory.from_bytes(16584333312 + 40860802176),
+    #     n_layers=60,  # Qwen has 60 transformer blocks (all joint-style)
+    #     hidden_size=1,
+    #     supports_tensor=False,
+    #     tasks=[ModelTask.ImageToImage],
+    #     components=[
+    #         ComponentInfo(
+    #             component_name="text_encoder",
+    #             component_path="text_encoder/",
+    #             storage_size=Memory.from_kb(16584333312),
+    #             n_layers=12,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,  # Single file
+    #         ),
+    #         ComponentInfo(
+    #             component_name="transformer",
+    #             component_path="transformer/",
+    #             storage_size=Memory.from_bytes(40860802176),
+    #             n_layers=60,
+    #             can_shard=True,
+    #             safetensors_index_filename="diffusion_pytorch_model.safetensors.index.json",
+    #         ),
+    #         ComponentInfo(
+    #             component_name="vae",
+    #             component_path="vae/",
+    #             storage_size=Memory.from_kb(0),
+    #             n_layers=None,
+    #             can_shard=False,
+    #             safetensors_index_filename=None,
+    #         ),
+    #     ],
+    # ),
 }
 
 

src/exo/worker/download/impl_shard_downloader.py

@@ -19,7 +19,7 @@ def exo_shard_downloader(max_parallel_downloads: int = 8) -> ShardDownloader:
 
 
 async def build_base_shard(model_id: ModelId) -> ShardMetadata:
-    model_card = await ModelCard.from_hf(model_id)
+    model_card = await ModelCard.load(model_id)
     return PipelineShardMetadata(
         model_card=model_card,
         device_rank=0,