Merge pull request #4144 from liutyi/dev

update SANA, Chroma, Cosmos cover images

html/reference.json

@@ -287,13 +287,13 @@
   "NVLabs Sana 1.5 1.6B 1k": {
     "path": "Efficient-Large-Model/SANA1.5_1.6B_1024px_diffusers",
     "desc": "Sana is an efficient model with scaling of training-time and inference time techniques. SANA-1.5 delivers: efficient model growth from 1.6B Sana-1.0 model to 4.8B, achieving similar or better performance than training from scratch and saving 60% training cost; efficient model depth pruning, slimming any model size as you want; powerful VLM selection based inference scaling, smaller model+inference scaling > larger model.",
-    "preview": "Efficient-Large-Model--Sana15_1600M_1024px_diffusers.jpg",
+    "preview": "Efficient-Large-Model--SANA1.5_1.6B_1024px_diffusers.jpg",
     "skip": true
   },
   "NVLabs Sana 1.5 4.8B 1k": {
     "path": "Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers",
     "desc": "Sana is an efficient model with scaling of training-time and inference time techniques. SANA-1.5 delivers: efficient model growth from 1.6B Sana-1.0 model to 4.8B, achieving similar or better performance than training from scratch and saving 60% training cost; efficient model depth pruning, slimming any model size as you want; powerful VLM selection based inference scaling, smaller model+inference scaling > larger model.",
-    "preview": "Efficient-Large-Model--Sana15_4800M_1024px_diffusers.jpg",
+    "preview": "Efficient-Large-Model--SANA1.5_4.8B_1024px_diffusers.jpg",
     "skip": true
   },
   "NVLabs Sana 1.5 1.6B 1k Sprint": {
@@ -305,25 +305,25 @@
   "NVLabs Sana 1.0 1.6B 4k": {
     "path": "Efficient-Large-Model/Sana_1600M_4Kpx_BF16_diffusers",
     "desc": "Sana is a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU.",
-    "preview": "Efficient-Large-Model--Sana15_1600M_4Kpx_diffusers.jpg",
+    "preview": "Efficient-Large-Model--Sana_1600M_4Kpx_BF16_diffusers.jpg",
     "skip": true
   },
   "NVLabs Sana 1.0 1.6B 2k": {
     "path": "Efficient-Large-Model/Sana_1600M_2Kpx_BF16_diffusers",
     "desc": "Sana is a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU.",
-    "preview": "Efficient-Large-Model--Sana1_1600M_2Kpx_diffusers.jpg",
+    "preview": "Efficient-Large-Model--Sana_1600M_2Kpx_BF16_diffusers.jpg",
     "skip": true
   },
   "NVLabs Sana 1.0 1.6B 1k": {
     "path": "Efficient-Large-Model/Sana_1600M_1024px_diffusers",
     "desc": "Sana is a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU.",
-    "preview": "Efficient-Large-Model--Sana1_1600M_1024px_diffusers.jpg",
+    "preview": "Efficient-Large-Model--Sana_1600M_1024px_diffusers.jpg",
     "skip": true
   },
   "NVLabs Sana 1.0 0.6B 0.5k": {
     "path": "Efficient-Large-Model/Sana_600M_512px_diffusers",
     "desc": "Sana is a text-to-image framework that can efficiently generate images up to 4096 × 4096 resolution. Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, deployable on laptop GPU.",
-    "preview": "Efficient-Large-Model--Sana1_600M_1024px_diffusers.jpg",
+    "preview": "Efficient-Large-Model--Sana_600M_512px_diffusers.jpg",
     "skip": true
   },