Trained for 1 epochs and 1500 steps.

Trained with datasets ['text-embeds', 'mj-v6']
Learning rate 8e-06, batch size 32, and 4 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
VAE: madebyollin/sdxl-vae-fp16-fix

README.md

@@ -15,11 +15,166 @@ widget:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_0_0.png
-- text: 'ethnographic photography of teddy bear at a picnic'
+- text: 'a woman sitting on the grass'
   parameters:
     negative_prompt: 'blurry, cropped, ugly'
   output:
     url: ./assets/image_1_0.png
+- text: 'a professional photo headshot of a man in studio lighting'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_2_0.png
+- text: 'a person holding a sign that reads ''SOON'''
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_3_0.png
+- text: 'Alien marketplace, bizarre creatures, exotic goods, vibrant colors, otherworldly atmosphere'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_4_0.png
+- text: 'Child holding a balloon, happy expression, colorful balloons, sunny day, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_5_0.png
+- text: 'a 4-panel comic strip showing an orange cat saying the words ''HELP'' and ''LASAGNA'''
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_6_0.png
+- text: 'a hand is holding a comic book with a cover that reads ''The Adventures of Superhero'''
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_7_0.png
+- text: 'Underground cave filled with crystals, glowing lights, reflective surfaces, fantasy environment, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_8_0.png
+- text: 'Bustling cyberpunk bazaar, vendors, neon signs, advanced tech, crowded, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_9_0.png
+- text: 'Cyberpunk hacker in a dark room, neon glow, multiple screens, intense focus, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_10_0.png
+- text: 'a cybernetic anne of green gables with neural implant and bio mech augmentations'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_11_0.png
+- text: 'Post-apocalyptic cityscape, ruined buildings, overgrown vegetation, dark and gritty, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_12_0.png
+- text: 'Magical castle in a lush forest, glowing windows, fantasy architecture, high resolution, detailed textures'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_13_0.png
+- text: 'Ruins of an ancient temple in an enchanted forest, glowing runes, mystical creatures, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_14_0.png
+- text: 'Mystical forest, glowing plants, fairies, magical creatures, fantasy art, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_15_0.png
+- text: 'Magical garden with glowing flowers, fairies, serene atmosphere, detailed plants, high resolution'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_16_0.png
+- text: 'Whimsical garden filled with fairies, magical plants, sparkling lights, serene atmosphere, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_17_0.png
+- text: 'Majestic dragon soaring through the sky, detailed scales, dynamic pose, fantasy art, high resolution'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_18_0.png
+- text: 'Fantasy world, floating islands in the sky, waterfalls, lush vegetation, detailed landscape, high resolution'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_19_0.png
+- text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_20_0.png
+- text: 'Space battle scene, starships fighting, laser beams, explosions, cosmic background'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_21_0.png
+- text: 'Abandoned fairground at night, eerie rides, ghostly figures, fog, dark atmosphere, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_22_0.png
+- text: 'Spooky haunted mansion on a hill, dark and eerie, glowing windows, ghostly atmosphere, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_23_0.png
+- text: 'a hardcover physics textbook that is called PHYSICS FOR DUMMIES'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_24_0.png
+- text: 'Epic medieval battle, knights in armor, dynamic action, detailed landscape, high resolution'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_25_0.png
+- text: 'Bustling medieval market with merchants, knights, and jesters, vibrant colors, detailed'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_26_0.png
+- text: 'Cozy medieval tavern, warm firelight, adventurers drinking, detailed interior, rustic atmosphere'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_27_0.png
+- text: 'Futuristic city skyline at night, neon lights, cyberpunk style, high contrast, sharp focus'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_28_0.png
+- text: 'Forest with neon-lit trees, glowing plants, bioluminescence, surreal atmosphere, high detail'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_29_0.png
+- text: 'Bright neon sign in a busy city street, ''Open 24 Hours'', bold typography, glowing lights'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_30_0.png
+- text: 'Retro diner sign, ''Joe''s Diner'', classic 1950s design, neon lights, weathered look'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_31_0.png
+- text: 'Vintage store sign with elaborate typography, ''Antique Shop'', hand-painted, weathered look'
+  parameters:
+    negative_prompt: 'blurry, cropped, ugly'
+  output:
+    url: ./assets/image_32_0.png
 ---
 
 # pixart-training
@@ -28,11 +183,11 @@ This is a full rank finetune derived from [PixArt-alpha/PixArt-Sigma-XL-2-1024-M
 
 
 
-The main validation prompt used during training was:
+No validation prompt was used during training.
+
+
+None
 
-```
-ethnographic photography of teddy bear at a picnic
-```
 
 ## Validation settings
 - CFG: `7.5`
@@ -55,12 +210,12 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 0
-- Training steps: 1000
+- Training epochs: 1
+- Training steps: 1500
 - Learning rate: 8e-06
-- Effective batch size: 96
+- Effective batch size: 128
   - Micro-batch size: 32
-  - Gradient accumulation steps: 3
+  - Gradient accumulation steps: 4
   - Number of GPUs: 1
 - Prediction type: epsilon
 - Rescaled betas zero SNR: False
@@ -73,7 +228,7 @@ You may reuse the base model text encoder for inference.
 
 ### mj-v6
 - Repeats: 0
-- Total number of images: 199872
+- Total number of images: 134144
 - Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: False
@@ -91,7 +246,7 @@ from diffusers import DiffusionPipeline
 
 
 model_id = "pixart-training"
-prompt = "ethnographic photography of teddy bear at a picnic"
+prompt = "An astronaut is riding a horse through the jungles of Thailand."
 negative_prompt = "malformed, disgusting, overexposed, washed-out"
 
 pipeline = DiffusionPipeline.from_pretrained(model_id)

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1597106775343a8153b308b4b7427f3f5469d1ae70ad04c6b7f6723dac36c0ac
+oid sha256:b59ab5187438495f70ae65205ab85b3a89c32121446239c4451ad44ba69f8ac9
 size 3665677155

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f3b1a5f95dcc31f7a44acf2784e0d3aa219fd4a333ac008412483e4063a5218
+oid sha256:0095adc498355bd439cad9421b34a6d1c1d09f12fa9ef8fd47d6aa43a9d63704
 size 14344

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a778f242057a9963f512d7713fc392bdaa1ea385692a6d218868f2e42ea21ee4
+oid sha256:5e9401b92a0437e861b78763e41ede39d20dc2bdd763568f11b5463d73323d27
 size 1000

training_state-mj-v6.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974645e8da8c2abdafe9545abe09d332633eaabd17909676477a3d68faa60c51
-size 23062435
+oid sha256:6f29ad928d40ef0bf3d488cdb9aaba3bcfb1d1cd94e268087cdeea897542a6a7
+size 12312675

training_state.json

@@ -1 +1 @@
-{"global_step": 1000, "epoch_step": 1000, "epoch": 1, "exhausted_backends": [], "repeats": {}}
+{"global_step": 1500, "epoch_step": 201, "epoch": 2, "exhausted_backends": [], "repeats": {"mj-v6": 0}}

transformer/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "PixArtTransformer2DModel",
   "_diffusers_version": "0.29.0",
-  "_name_or_path": "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
+  "_name_or_path": "/home/ubuntu/code/MJ/mjv6/models/checkpoint-1000",
   "activation_fn": "gelu-approximate",
   "attention_bias": true,
   "attention_head_dim": 72,

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0404e972345ceaa2b6cdcd3c8022a93e9a66475833776d91fabd3e3dab0a5fdf
+oid sha256:c7bfe5b2c7ab5cc1d27949b595d1844abedaa050fec5fc4a7ac68124c21ca0af
 size 1221780352