Publish MOSS-Image SFT AnyFlow recipes, adapters, and validation previews

.gitattributes

@@ -1289,3 +1289,19 @@ validation_images/step_51500_portrait_0_512x512.png filter=lfs diff=lfs merge=lf
 validation_images/step_51500_portrait_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
 validation_images/step_51500_text_0_512x512.png filter=lfs diff=lfs merge=lfs -text
 validation_images/step_51500_text_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_character_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_character_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_photo_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_photo_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_portrait_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_portrait_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_text_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-52000/assets/step_52000_text_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_character_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_character_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_photo_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_photo_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_portrait_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_portrait_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_text_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_52000_text_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -12,7 +12,7 @@ tags:
 
 Forward MeanFlow pretraining. Stage 2 initializes from the final EMA adapter.
 
-Status: **training**. Observed updates: 51,570 / 100,000.
+Status: **training**. Observed updates: 52,090 / 100,000.
 
 ## Training recipe
 
@@ -49,11 +49,11 @@ Schedule correction: the stage-1 run resumed from update 1,000 with the [flow-sc
 
 [Pre-correction previews](pre-schedule-fix/validation_images) remain available.
 
-[1,000](checkpoint-1000), [2,000](checkpoint-2000), [3,000](checkpoint-3000), [4,000](checkpoint-4000), [5,000](checkpoint-5000), [6,000](checkpoint-6000), [7,000](checkpoint-7000), [8,000](checkpoint-8000), [9,000](checkpoint-9000), [10,000](checkpoint-10000), [11,000](checkpoint-11000), [12,000](checkpoint-12000), [13,000](checkpoint-13000), [14,000](checkpoint-14000), [15,000](checkpoint-15000), [16,000](checkpoint-16000), [17,000](checkpoint-17000), [18,000](checkpoint-18000), [19,000](checkpoint-19000), [20,000](checkpoint-20000), [21,000](checkpoint-21000), [22,000](checkpoint-22000), [23,000](checkpoint-23000), [24,000](checkpoint-24000), [25,000](checkpoint-25000), [26,000](checkpoint-26000), [27,000](checkpoint-27000), [28,000](checkpoint-28000), [29,000](checkpoint-29000), [30,000](checkpoint-30000), [31,000](checkpoint-31000), [32,000](checkpoint-32000), [33,000](checkpoint-33000), [34,000](checkpoint-34000), [35,000](checkpoint-35000), [36,000](checkpoint-36000), [37,000](checkpoint-37000), [38,000](checkpoint-38000), [39,000](checkpoint-39000), [40,000](checkpoint-40000), [41,000](checkpoint-41000), [42,000](checkpoint-42000), [43,000](checkpoint-43000), [44,000](checkpoint-44000), [45,000](checkpoint-45000), [46,000](checkpoint-46000), [47,000](checkpoint-47000), [48,000](checkpoint-48000), [49,000](checkpoint-49000), [50,000](checkpoint-50000), [51,000](checkpoint-51000)
+[1,000](checkpoint-1000), [2,000](checkpoint-2000), [3,000](checkpoint-3000), [4,000](checkpoint-4000), [5,000](checkpoint-5000), [6,000](checkpoint-6000), [7,000](checkpoint-7000), [8,000](checkpoint-8000), [9,000](checkpoint-9000), [10,000](checkpoint-10000), [11,000](checkpoint-11000), [12,000](checkpoint-12000), [13,000](checkpoint-13000), [14,000](checkpoint-14000), [15,000](checkpoint-15000), [16,000](checkpoint-16000), [17,000](checkpoint-17000), [18,000](checkpoint-18000), [19,000](checkpoint-19000), [20,000](checkpoint-20000), [21,000](checkpoint-21000), [22,000](checkpoint-22000), [23,000](checkpoint-23000), [24,000](checkpoint-24000), [25,000](checkpoint-25000), [26,000](checkpoint-26000), [27,000](checkpoint-27000), [28,000](checkpoint-28000), [29,000](checkpoint-29000), [30,000](checkpoint-30000), [31,000](checkpoint-31000), [32,000](checkpoint-32000), [33,000](checkpoint-33000), [34,000](checkpoint-34000), [35,000](checkpoint-35000), [36,000](checkpoint-36000), [37,000](checkpoint-37000), [38,000](checkpoint-38000), [39,000](checkpoint-39000), [40,000](checkpoint-40000), [41,000](checkpoint-41000), [42,000](checkpoint-42000), [43,000](checkpoint-43000), [44,000](checkpoint-44000), [45,000](checkpoint-45000), [46,000](checkpoint-46000), [47,000](checkpoint-47000), [48,000](checkpoint-48000), [49,000](checkpoint-49000), [50,000](checkpoint-50000), [51,000](checkpoint-51000), [52,000](checkpoint-52000)
 
 [All validation previews](validation_images) include live and EMA comparisons at both resolutions.
 
-Latest live adapter: [update 51,000](checkpoint-51000/pytorch_lora_weights.safetensors).
+Latest live adapter: [update 52,000](checkpoint-52000/pytorch_lora_weights.safetensors).
 
 ## Inference
 

checkpoint-52000/ema/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a995cac29862af9ff8300ab299ea3abdd01cf49a8b4e7108721d96a8333165
+size 294180952

checkpoint-52000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c246a03f89464fc0f6fb529eee4e6639e7340445ad7777a422446342dcb313
+size 294180952

publication.json

@@ -203,10 +203,14 @@
     "51000": {
       "live": "b3994696843a8941fc7586aab81e6686cc31f28ed04f03d42be57568f1daf699",
       "ema": "45fefb949b74ba7204e6d6ab9c5febf50344f49d761e035e78d06abe289eb069"
+    },
+    "52000": {
+      "live": "09c246a03f89464fc0f6fb529eee4e6639e7340445ad7777a422446342dcb313",
+      "ema": "b0a995cac29862af9ff8300ab299ea3abdd01cf49a8b4e7108721d96a8333165"
     }
   },
   "state": "training",
-  "step": 51570,
+  "step": 52090,
   "previews": [
     "validation_images/step_0_character_0_512x512.png",
     "validation_images/step_0_character_1_1024x1024.png",
@@ -968,6 +972,14 @@
     "validation_images/step_51500_portrait_1_1024x1024.png",
     "validation_images/step_51500_text_0_512x512.png",
     "validation_images/step_51500_text_1_1024x1024.png",
+    "validation_images/step_52000_character_0_512x512.png",
+    "validation_images/step_52000_character_1_1024x1024.png",
+    "validation_images/step_52000_photo_0_512x512.png",
+    "validation_images/step_52000_photo_1_1024x1024.png",
+    "validation_images/step_52000_portrait_0_512x512.png",
+    "validation_images/step_52000_portrait_1_1024x1024.png",
+    "validation_images/step_52000_text_0_512x512.png",
+    "validation_images/step_52000_text_1_1024x1024.png",
     "validation_images/step_5500_character_0_512x512.png",
     "validation_images/step_5500_character_1_1024x1024.png",
     "validation_images/step_5500_photo_0_512x512.png",