Upload with huggingface_hub

Miwano_Rag-8000-fp16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ee1a7fde77a2fa0a38a373d3d0813a9ab71fd07bd4ae3597efbfa1dc45be9f
+size 2132856622

README.md

@@ -0,0 +1,13 @@
+---
+license: creativeml-openrail-m
+tags:
+- text-to-image
+- stable-diffusion
+---
+### Model Dreambooth concept Miwano_Rag-8000 được train bởi hr16 bằng [Shinja Zero SoTA DreamBooth_Stable_Diffusion](https://colab.research.google.com/drive/1G7qx6M_S1PDDlsWIMdbZXwdZik6sUlEh) notebook <br>
+
+
+Test concept bằng [Shinja Zero no Notebook](https://colab.research.google.com/drive/1Hp1ZIjPbsZKlCtomJVmt2oX7733W44b0) <br>
+Hoặc test bằng `diffusers` [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb)
+
+Ảnh mẫu của concept: WIP

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.8.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.8.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "trained_betas": null
+}

state/args.yaml

@@ -0,0 +1,78 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+center_crop: false
+class_data_dir: /content/class-images
+class_insert_pos_regex: null
+class_negative_prompt: lowres, bad anatomy, bad hands, text, error, missing fingers,
+  extra digit, fewer digits, cropped, worst quality, low quality, normal quality,
+  jpeg artifacts, signature, watermark, username, blurry
+class_prompt: masterpiece, best quality, ultra-detailed, 1girl
+clip_skip: 2
+concepts_list:
+- class_data_dir: /content/class-images
+  class_negative_prompt: lowres, bad anatomy, bad hands, text, error, missing fingers,
+    extra digit, fewer digits, cropped, worst quality, low quality, normal quality,
+    jpeg artifacts, signature, watermark, username, blurry
+  class_prompt: masterpiece, best quality, ultra-detailed, 1girl
+  instance_data_dir: /content/drive/MyDrive/miwano_rag_512x512_
+  instance_prompt: masterpiece, best quality, ultra-detailed, 1girl, by Miwano_Rag
+config: null
+debug_arb: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+gradient_clipping: false
+guidance_scale: 11.0
+infer_batch_size: 2
+infer_steps: 28
+instance_data_dir: /content/drive/MyDrive/miwano_rag_512x512_
+instance_insert_pos_regex: null
+instance_prompt: masterpiece, best quality, ultra-detailed, 1girl, by Miwano_Rag
+last_epoch: -1
+learning_rate: 1.0e-06
+local_rank: -1
+lr_cycles: 1
+lr_scheduler: cosine_with_restarts
+lr_warmup_steps: 700
+max_grad_norm: 1.0
+max_train_steps: 5000
+mixed_precision: fp16
+n_save_sample: 4
+not_cache_latents: false
+num_class_images: 100
+num_train_epochs: 13
+optimizer: adamw_8bit
+output_dir: /content/Miwano_Rag
+pad_tokens: true
+pretrained_model_name_or_path: Miwano_Rag/9JGG8ER/5000
+pretrained_vae_name_or_path: Miwano_Rag/9JGG8ER/5000/vae
+prior_loss_weight: 1.0
+read_prompt_from_txt: null
+resolution: 512
+resume: true
+rm_after_wandb_saved: false
+run_id: null
+sample_interval: null
+save_interval: 500
+save_interval_epochs: 10
+save_min_steps: 3000
+save_sample_negative_prompt: lowres, bad anatomy, bad hands, text, error, missing
+  fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal
+  quality, jpeg artifacts, signature, watermark, username, blurry
+save_sample_prompt: masterpiece, best quality, 1girl, by Miwano_Rag
+save_unet_half: true
+scale_lr: true
+scale_lr_linear: false
+seed: 17082006
+sgd_dampening: 0
+sgd_momentum: 0.9
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_aspect_ratio_bucket: false
+wandb: false
+wandb_artifact: false
+wandb_project: SD-Dreambooth-HF
+wandb_sample: true
+weight_decay: 0.01
+with_prior_preservation: true

state/state.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7de1d0ff48a2a44d6c27767e73dedd4c42ccfc02701ec0f7e32675bcb936d6d
+size 1725803333

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "Miwano_Rag/9JGG8ER/5000",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3601d42ec0bd321daf5bedc25122f888ede6fd1492de53b736c2ba78cdb99f3f
+size 492307041

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "Miwano_Rag/9JGG8ER/5000/tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.8.0.dev0",
+  "_name_or_path": "Miwano_Rag/9JGG8ER/5000",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 32,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db559d221fd28d906f605e800ef451de7eb36d0aba49e217524da41a919062da
+size 1719334053

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.8.0.dev0",
+  "_name_or_path": "Miwano_Rag/9JGG8ER/5000/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e174991e5609bc5c2b3995e3f223fb2c5f0ae3be307fa9591b351d837a08770
+size 334711857