Upload Tardisfusion-v2.ckpt (#2)

- Upload Tardisfusion-v2.ckpt (434c94c2bc7d8878ea17944ff66e92f951e62b05)
- Upload 11 files (f45a2a88ab35dea411bcfd2e0ae678874a66678b)
- Rename preprocessor_config.json to feature_extractor/preprocessor_config.json (bf6dc0b2f312dad2786e414ffba6762c3986adb1)
- Rename scheduler_config.json to scheduler/scheduler_config.json (16a5d827b3a399e6343fb30d8e16b366c7ce3d99)
- Rename config.json to text_encoder/config.json (24761c21fa1499128e699ac037c229dbbe349980)
- Delete pytorch_model.bin (088400d54777595eebad563124b42b719b778c35)
- Upload pytorch_model.bin (7431fc3039b5377d54b56b18cf9d27c6378326fb)
- Delete merges.txt (cb0e7f8817c81eb4856902c97cf74e6cbc7b2d52)
- Rename special_tokens_map.json to tokenizer/special_tokens_map.json (67fe7e7c28e460361057cca7749421df91eb3ca4)
- Rename tokenizer_config.json to tokenizer/tokenizer_config.json (5b212972e870301d3bafc361146ff8887c665a59)
- Delete vocab.json (c046fbb37da6b0ecef0fbf6d62d357f8a53b48f4)
- Upload 2 files (15ffa6999f57654913388f3dfd4c808e8a35e8e6)
- Delete diffusion_pytorch_model.bin (4833fec746ed4c536d377030d4b6b22e128f5e59)
- Create tokenizer/config.json (47162f072f31babf62120eeced4745e25b44ae78)
- Rename tokenizer/config.json to unet/config.json (d74b53381b8687fcfde14f0f43ccbd433f06665a)
- Upload diffusion_pytorch_model.bin (2247339202cf42769a05be75a5da7fa74f990928)
- Create vae/config.json (78aa3c5a1a11e9bfd246143f8492fc77b8efef7a)
- Upload diffusion_pytorch_model.bin (64f70f74ba5283011907696b82b001a1fddc4a5a)
- Update README.md (998561d765d73f7ccc10948a4dd5e2945cbc49db)
- Upload showcase.jpg (cb9ac46015d39ccbfe464a9ece52f81f6bae9ad6)

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 Tardisfusion-v1.ckpt filter=lfs diff=lfs merge=lfs -text
+Tardisfusion-v2.ckpt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,37 @@
 ---
-license: openrail
+license: creativeml-openrail-m
 ---
 
-This model intends to replicate the generic style of the interior of a TARDIS. The first dataset (82 pictures) focusses on the console a little too much, but training 2k steps only helped complete what was already in the original model this was based on, RunwayML 1.5
-All doctor who seasons were used, with no distinction in the prompt.
+# TARDISfusion
+<p>
+	<img src="https://huggingface.co/Guizmus/Tardisfusion/raw/main/showcase.jpg"/><br/>
+	This is a Dreamboothed Stable Diffusion model trained on 3 Style concepts.<br/>
+	The total dataset is made of 209 pictures, and the training has been done on runawayml 1.5 with 2500 steps and the new VAE.
+	The following tokens will add their corresponding concept :<br/>
+	<ul>
+		<li><b>Classic Tardis style</b> : Architectural and furniture style seen inside the TARDIS in the series before the reboot.</li>
+		<li><b>Modern Tardis style</b>: Architectural and furniture style seen inside the TARDIS in the series after the reboot</li>
+		<li><b>Tardis Box style</b>: A style made from the TARDIS seen from the outside. Summons a TARDIS anywhere.</li>
+	</ul>
+</p>
 
-* Recommended sampling method : DPM2 a Karras, Euler a
-* Activation token : TardisRoom style
-* Best used on img2img
-* [download link](https://huggingface.co/Guizmus/Tardisfusion/resolve/main/Tardisfusion-v1.ckpt)
+## 🧨 Diffusers
 
-This first version is still rough, better ones should come soon.
+This model can be used just like any other Stable Diffusion model. For more information,
+please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
+
+You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
+
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+
+model_id = "Guizmus/Tardisfusion"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+prompt = "a bedroom, Classic Tardis style"
+image = pipe(prompt).images[0]
+
+image.save("./TARDIS Style.png")
+```

Tardisfusion-v2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7dd51bc640826a4ed8b724153d548270e4a2fc725fa08a110cc7b4e300c6b62
+size 2132871991

args.json

@@ -0,0 +1,70 @@
+{
+  "pretrained_model_name_or_path": "F:/AI/Diffusers/stable-diffusion-v1-5",
+  "pretrained_vae_name_or_path": null,
+  "revision": "fp16",
+  "tokenizer_name": null,
+  "instance_data_dir": null,
+  "class_data_dir": null,
+  "instance_prompt": null,
+  "class_prompt": null,
+  "save_sample_prompt": "a bedroom,modern tardis style",
+  "save_sample_negative_prompt": null,
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "pad_tokens": false,
+  "with_prior_preservation": true,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 100,
+  "output_dir": "F:/AI/Outputs/Dreambooth/Tardisfusion",
+  "seed": 42,
+  "resolution": 512,
+  "center_crop": false,
+  "train_text_encoder": true,
+  "train_batch_size": 1,
+  "sample_batch_size": 8,
+  "num_train_epochs": 9,
+  "max_train_steps": 2500,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": true,
+  "learning_rate": 1e-06,
+  "scale_lr": false,
+  "lr_scheduler": "constant",
+  "lr_warmup_steps": 0,
+  "use_8bit_adam": false,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_weight_decay": 0.01,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_model_id": null,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 500,
+  "save_min_steps": 0,
+  "mixed_precision": "no",
+  "not_cache_latents": false,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "Classic Tardis style",
+      "instance_data_dir": "F:/AI/Datasets/DrWho/ClassicTardis",
+      "class_prompt": "black and white style",
+      "class_data_dir": "F:/AI/Datasets/Regularisation/BlackNWhiteStyle"
+    },
+    {
+      "instance_prompt": "Modern Tardis style",
+      "instance_data_dir": "F:/AI/Datasets/DrWho/ModernTardis",
+      "class_prompt": "strange style",
+      "class_data_dir": "F:/AI/Datasets/Regularisation/StrangeStyle"
+    },
+    {
+      "instance_prompt": "Tardis Box style",
+      "instance_data_dir": "F:/AI/Datasets/DrWho/ExteriorTardis",
+      "class_prompt": "a phonebooth",
+      "class_data_dir": "F:/AI/Datasets/Regularisation/APhonebooth"
+    }
+  ]
+}

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.7.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "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": "0.7.0.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
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "F:/AI/Diffusers/stable-diffusion-v1-5",
+  "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:ef8c57f31a2369b3596623bd9eb4c9b9eb7247a3f8b889f1a758f49d45c2e949
+size 492309793

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": "F:/AI/Diffusers/stable-diffusion-v1-5\\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": "0.7.0.dev0",
+  "_name_or_path": "F:/AI/Diffusers/stable-diffusion-v1-5",
+  "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": 64,
+  "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:ce9cdc6acb9b8792a9f2cea06090107f1b2e2ec8892ce56fcad86381ce0aa9af
+size 3438375973

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.7.0.dev0",
+  "_name_or_path": "F:/AI/Diffusers/stable-diffusion-v1-5",
+  "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 sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
+size 334711857