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

.gitattributes

@@ -785,3 +785,19 @@ validation_images/step_30500_portrait_0_512x512.png filter=lfs diff=lfs merge=lf
 validation_images/step_30500_portrait_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
 validation_images/step_30500_text_0_512x512.png filter=lfs diff=lfs merge=lfs -text
 validation_images/step_30500_text_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_character_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_character_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_photo_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_photo_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_portrait_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_portrait_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_text_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+checkpoint-31000/assets/step_31000_text_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_character_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_character_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_photo_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_photo_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_portrait_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_portrait_1_1024x1024.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_text_0_512x512.png filter=lfs diff=lfs merge=lfs -text
+validation_images/step_31000_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: 30,530 / 100,000.
+Status: **training**. Observed updates: 31,040 / 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)
+[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)
 
 [All validation previews](validation_images) include live and EMA comparisons at both resolutions.
 
-Latest live adapter: [update 30,000](checkpoint-30000/pytorch_lora_weights.safetensors).
+Latest live adapter: [update 31,000](checkpoint-31000/pytorch_lora_weights.safetensors).
 
 ## Inference
 

checkpoint-31000/ema/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027e69efae49281d346d9a72bf31d651c1b5e287c0d9ec5edb11b6c88a8af2d3
+size 294180952

checkpoint-31000/pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69af92574aee4ef7f9c7c0206ef88dc95fd2cb1f4f9f52e10c32d0616b41665d
+size 294180952

publication.json

@@ -119,10 +119,14 @@
     "30000": {
       "live": "90305365ba57b8361d784e5847978e035bc001dd15321b6d419f4b962ca892b0",
       "ema": "4bf1e355d238ff64591532b74f1c9c93db86059d95b41414c5ffb294c4ed535d"
+    },
+    "31000": {
+      "live": "69af92574aee4ef7f9c7c0206ef88dc95fd2cb1f4f9f52e10c32d0616b41665d",
+      "ema": "027e69efae49281d346d9a72bf31d651c1b5e287c0d9ec5edb11b6c88a8af2d3"
     }
   },
   "state": "training",
-  "step": 30530,
+  "step": 31040,
   "previews": [
     "validation_images/step_0_character_0_512x512.png",
     "validation_images/step_0_character_1_1024x1024.png",
@@ -508,6 +512,14 @@
     "validation_images/step_30500_portrait_1_1024x1024.png",
     "validation_images/step_30500_text_0_512x512.png",
     "validation_images/step_30500_text_1_1024x1024.png",
+    "validation_images/step_31000_character_0_512x512.png",
+    "validation_images/step_31000_character_1_1024x1024.png",
+    "validation_images/step_31000_photo_0_512x512.png",
+    "validation_images/step_31000_photo_1_1024x1024.png",
+    "validation_images/step_31000_portrait_0_512x512.png",
+    "validation_images/step_31000_portrait_1_1024x1024.png",
+    "validation_images/step_31000_text_0_512x512.png",
+    "validation_images/step_31000_text_1_1024x1024.png",
     "validation_images/step_3500_character_0_512x512.png",
     "validation_images/step_3500_character_1_1024x1024.png",
     "validation_images/step_3500_photo_0_512x512.png",