Trained for 0 epochs and 20500 steps.

Trained with datasets ['text-embeds-pixart-filter', 'photo-concept-bucket', 'moviecollection', 'experimental', 'ethnic', 'sports', 'architecture', 'shutterstock', 'cinemamix-1mp', 'nsfw-1024', 'anatomy', 'bg20k-1024', 'yoga', 'photo-aesthetics', 'text-1mp', 'movieposters', 'normalnudes', 'pixel-art', 'signs', 'midjourney-v6-520k-raw', 'sfwbooru', 'nijijourney-v6-520k-raw', 'dalle3']
Learning rate 1e-06, batch size 24, and 1 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' timestep spacing.
Base model: ptx0/pixart-900m-1024-ft-large
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -77,7 +77,7 @@ You may reuse the base model text encoder for inference.
 ## Training settings
 
 - Training epochs: 0
-- Training steps: 20000
+- Training steps: 20500
 - Learning rate: 1e-06
 - Effective batch size: 192
   - Micro-batch size: 24
@@ -94,7 +94,7 @@ You may reuse the base model text encoder for inference.
 
 ### photo-concept-bucket
 - Repeats: 0
-- Total number of images: ~703040
+- Total number of images: ~567360
 - Total number of aspect buckets: 3
 - Resolution: 1.0 megapixels
 - Cropped: True

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7f446ad7db6b9dd0b02a1fd631860aed4bc7642cbb69be223461d7def25914
+oid sha256:17d3d0493eecfb8aca716213ad7061345b6cc42cf3712d07243fc89441a10007
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:047f6604b01004028fdb3af7f712a3a40186b7a05c1578ca95eb503258c70536
-size 16036
+oid sha256:25731035249ec3a5a4f664b549992b187dcf02232f87ddc9597fa4b956311a5e
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45e09806cd58a43677a8d871a2183232641b74992395e00cb39c296107b65013
+oid sha256:da5e063768a4bb2c65d9be8a31b9860c3a2d7ed243402d61627aece690c87fba
 size 1000

training_state-dalle3.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b649d1f29729ed989b3d322e0d7675ba2ecd664b03914c34be4eda0704aac8
-size 14871424
+oid sha256:593b54c0982458c8799f69bb5acaf48d05ea0c8d2dacdd03faf88affff789c59
+size 15227885

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7715023106434d5e26445bed5b97f372dbb0c55f806dd33affa8ae6cea81611
-size 11418307
+oid sha256:4d0dd0b3981a94c51981eb18993721939c302b481234a82a9760e470cd94602c
+size 5295068

training_state.json

@@ -1 +1 @@
-{"global_step": 20000, "epoch_step": 1, "epoch": 1, "exhausted_backends": ["signs", "nijijourney", "pixel-art", "propagandaposters", "sports", "gay", "experimental", "yoga", "ethnic", "cinemamix-1mp", "architecture", "mj-60", "normalnudes", "bookcovers", "celebrities", "movieposters", "shutterstock", "nsfw-1024", "photo-aesthetics", "moviecollection", "bg20k-1024", "anatomy", "sfwbooru", "midjourney-v6-520k-raw", "nijijourney-v6-520k-raw"], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 52, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0}}
+{"global_step": 20500, "epoch_step": 1, "epoch": 1, "exhausted_backends": ["signs", "nijijourney", "pixel-art", "propagandaposters", "sports", "gay", "experimental", "yoga", "ethnic", "cinemamix-1mp", "architecture", "mj-60", "normalnudes", "bookcovers", "celebrities", "movieposters", "shutterstock", "nsfw-1024", "photo-aesthetics", "moviecollection", "bg20k-1024", "anatomy", "sfwbooru", "midjourney-v6-520k-raw", "nijijourney-v6-520k-raw", "photo-concept-bucket"], "repeats": {"bookcovers": 0, "signs": 0, "normalnudes": 0, "nijijourney": 0, "movieposters": 0, "celebrities": 0, "pixel-art": 0, "propagandaposters": 0, "sports": 0, "moviecollection": 0, "gay": 0, "experimental": 0, "yoga": 0, "ethnic": 0, "cinemamix-1mp": 0, "architecture": 0, "mj-60": 0, "text-1mp": 55, "shutterstock": 0, "nsfw-1024": 0, "photo-aesthetics": 0, "anatomy": 0, "bg20k-1024": 0, "sfwbooru": 0, "midjourney-v6-520k-raw": 0, "nijijourney-v6-520k-raw": 0, "photo-concept-bucket": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615fd084554975fd351131fa66bddb67211a03cd97775e2e35f868ae45a4f9eb
+oid sha256:002c1f0c1905c23c006a5b5f9586c0df75168040374b64a91754907b69afa722
 size 1816969728