adding 3D style (#3)

- adding 3D style (f8c222e015d73189f0f9d56e67dd0a7b5f8494c5)
- Delete feature_extractor/preprocessor_config.json (600b633cc0c8256c7e508c625a695ad30f9adb45)
- Delete safety_checker/config.json (3bb7b526b50756a1215fe3d3b93e3c29bb606402)
- Delete safety_checker/pytorch_model.bin (144383ac0e548e6a019adebb03d51118a4d0bdec)
- Delete scheduler/scheduler_config.json (1c711b9d09c2c53b8faea0f1a3f320029bc42f59)
- Delete text_encoder/config.json (f1b1e7d061abcbf0f6ce5187f9815abf5640b69a)
- Delete text_encoder/pytorch_model.bin (36e1cf890820edc7a6b434668e612bc4cbb42615)
- Delete tokenizer/merges.txt (63ba2abe2257eabea389c832a39bd0db4c4f10a5)
- Delete tokenizer/special_tokens_map.json (57fcbbe33e0aead1ee8d80179252fdbdd5769c0b)
- Delete tokenizer/tokenizer_config.json (8e05e5ef62985ce795eb6512ddb6dd2d89f9a189)
- Delete tokenizer/vocab.json (0f9baa7d5016817d91c0393ba9bf9a985e2b6b6e)
- Delete unet/config.json (462281ff8c5ec7b06c907a5d281dd75441cc21be)
- Delete unet/diffusion_pytorch_model.bin (ac78d415853cbbf3b47104b6d306a06a52168f37)
- Delete vae/config.json (f37c02e080501b4eea56d63db81bcbad497ed7ab)
- Delete vae/diffusion_pytorch_model.bin (53e013e1157da9d92cc742034c60af1597f2d1eb)
- Delete model_index.json (8fcaa13d5b0e2606cc862bca8a9a9cdab7e0335a)
- Create images/init.txt (0f4f7999b268c6bd9b2ea785d14d53c8e8d4d904)
- Upload 2 files (128790a3e4638621e3ece88c6c3a84748c506c21)
- Delete showcase_AnimeChan.jpg (5b91f69c8a54d1bee47a5cc4939316d749515ee4)
- Update README.md (0f7f8298a2cc4c3d3344b3a9bc64187287a756e0)
- Delete images/init.txt (3156c46ce2ff8c0c7f99909935c34c4e67cba8b8)
- Create ckpt/init.txt (1b159725b0907d6c0075d04bf011ba0de04a6475)
- Upload 4 files (58331fd0f71784913bdc87c24413f6e195a132b9)
- Delete ckpt/AnimeChanStyle_v1.ckpt (c593296833f1fba536dbbd684669952f96ab492c)
- Upload AnimeChanStyle-v1.ckpt (ac5ca89086851c5cc854bd4c5f258a449b705aac)
- Delete ckpt/init.txt (aaf294b5cdc53795d1d3870063c7ce4ace3c2b45)
- Delete AnimeChan Style.zip (0149387ec67ed1c7b7a7d976c69cedce3a269911)
- Delete AnimeChanStyle-v2.ckpt (b72839865a3747527990a7926f29dba867004861)
- Delete AnimeChanStyle_v1.ckpt (29dc661a31775326d74bc290996373bdac365228)
- Delete showcase.jpg (bf74bb38acbdbaf96c9ad2e906c847c9d919ebb0)
- Create datasets/init.txt (e0f26b18b98065c55460401a2752626cb5c11dd0)
- Upload 3 files (af2f733927dba93cbad1fdddd798c139af16565a)
- Upload 4 files (805427d80e6556475d61bc47bb0a3d091437b6ac)
- Delete images/showcase_AnimeChan.jpg (a489b8d6e659ccf3b3b3da95cdbf11c3c5da8b3f)
- Delete images/showcase_3DChanStyle.jpg (3b66820ffeac2d5b565ddf3efb0042519afe6bf4)
- Delete datasets/init.txt (0d88997f8ee7ad98828a57f8ba0b9ab125c5f5fb)
- Upload README.md (151905fa36904b83eac769cf103ecaf1f2abdf6d)

README.md

@@ -2,46 +2,88 @@
 language:
 - en
 license: creativeml-openrail-m
-thumbnail: "https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/showcase_AnimeChan.jpg"
+thumbnail: "https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_main.jpg"
 tags:
 - stable-diffusion
 - text-to-image
 - image-to-image
 library_name: "EveryDream"
-datasets:
-- Guizmus/AnimeChanStyle
 inference: false
 ---
 
+# Introduction
+
+This is a collection of models made from and for the users of the Stable Diffusion Discord server. Different categories of channel exist, the "Dreamers Communities" presenting a panel of subjects, like Anime, 3D, or Architectural. Each of these channels has users posting images made through the use of Stable diffusion. After asking the users, and, depending on the activity of each channel, collecting a dataset from new submissions or from the history of the channel, I intend to build multiple models representing the style of each, so that users can produce things in the style they like and mix it with other things more easily.
+
+Those are mainly done through the use of EveryDream, and should result in a Mega Model towards the end for the datasets that are compatible. Some model like the Anime one require to stay on a different starting point, and may not get merged.
+
+
+
+# 3DChanStyle Style
+
+
+## Dataset & training
+
+This model was based on [RunwayML SD 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with updated VAE.
+
+The dataset was a collaborative effort of the Stable Diffusion #3D channel, made of pictures from the users themselves using their different techniques.
+
+120 total pictures in the dataset, 500 repeats total each, over 10 Epoch on LR1e-6.
+
+This was trained using EveryDream with a full caption of all training pictures.
+
+The style will be called by the use of the token **3D Style**.
+
+Other significant tokens : rick roll, fullbody shot, bad cosplay man
+
+## Showcase & Downloads
+
+![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_3DChanStyle-v1.jpg)
+
+[CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/3DStyle-v1.ckpt)
+
+[CKPT with training optimizers (11GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/3DStyle-v1_with_optimizers.ckpt)
+
+[Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/3DChanStyle-v1.zip)
+
+
+
 # AnimeChan Style
-<p>
-	<img alt="Showcase" src="https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/showcase_AnimeChan.jpg"/><br/>
-	This model was based on <a href="https://huggingface.co/naclbit/trinart_stable_diffusion_v2">Trinart</a> model.<br/>
-	The dataset was a collaborative effort of the Stable Diffusion #anime channel, made of pictures from the users themselves using their different techniques.<br/>
-	100 total pictures in the dataset, 300 repeats total each, over 6 Epoch on LR1e-6.<br/>
-	This was trained using EveryDream with a full caption of all training pictures. The dataset can be found <a href="https://huggingface.co/datasets/Guizmus/AnimeChanStyle">here</a>.<br/>
-	<br/>
-	The style will be called by the use of the token <b>AnimeChan Style</b>.<br/>
-	<br/>
-	To access this model, you can download the CKPT file below, or use the <a href="https://huggingface.co/Guizmus/AnimeChanStyle/tree/main">diffusers</a>
-</p>
 
-[current v2 download link](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/AnimeChanStyle-v2.ckpt)
+## Dataset & training
+
+This model was based on [Trinart](https://huggingface.co/naclbit/trinart_stable_diffusion_v2) model.
+
+The dataset was a collaborative effort of the Stable Diffusion #anime channel, made of pictures from the users themselves using their different techniques.
+
+100 total pictures in the dataset, 300 repeats total each, over 6 Epoch on LR1e-6.
+
+This was trained using EveryDream with a full caption of all training pictures.
+
+The style will be called by the use of the token **AnimeChan Style**.
+
+## Downloads v2
+
+![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_AnimeChan-v2.jpg)
+
+[CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/AnimeChanStyle-v2.ckpt)
+
+[Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/AnimeChanStyle-v2.zip)
+
+## Downloads v1
 
-[dataset for the second version](https://huggingface.co/datasets/Guizmus/AnimeChanStyle)
+![Showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/images/showcase_AnimeChan-v1.jpg)
 
-## First version
+[CKPT (2GB)](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/ckpt/AnimeChanStyle-v1.ckpt)
 
-![first version showcase](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/showcase.jpg)
+[Dataset](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/datasets/AnimeChanStyle-v1.zip)
 
-[first version download link](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/AnimeChanStyle_v1.ckpt)
 
-[dataset for the first version](https://huggingface.co/Guizmus/SD_DreamerCommunities_Collection/resolve/main/AnimeChan%20Style.zip)
 
 
-## License
+# License
 
-This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
+These models are open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
 The CreativeML OpenRAIL License specifies: 
 
 1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 

unet/diffusion_pytorch_model.bin → ckpt/3DStyle-v1.ckpt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ab275da85b3ff348e1e4a60cda864dc14acbb0676dd3f813160913c29bd740
-size 3438366373
+oid sha256:9698c46f614733b95d75cae29e777be15b2f13758f92d8eb113d566d79b665a6
+size 2132888989

safety_checker/pytorch_model.bin → ckpt/3DStyle-v1_with_optimizers.ckpt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
-size 1216064769
+oid sha256:8bca5d3ef403ad1ecfa7d3c9c5717a3bd5fa7899f93cd5526e4d55bbbd380147
+size 12126930715

text_encoder/pytorch_model.bin → datasets/3DChanStyle-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d9696908f0799f233577504bd321350000c0ccf236df5f9ebb7561a24af46e
-size 492307041
+oid sha256:0b659800b6b5140f8e953be05d7acd6d02296dbcbbd43dae944af84b2c5d131a
+size 29246736

vae/diffusion_pytorch_model.bin → datasets/AnimeChanStyle-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6723bacd3c60b11a2b4e6007338a54c6964c210116c3ccecb3bfc80e218afc8f
-size 334711857
+oid sha256:09f5678e615988ce35d01ce9980a546568e27ec52065d2578c265275b070ea27
+size 98956573

feature_extractor/preprocessor_config.json

@@ -1,20 +0,0 @@
-{
-  "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

@@ -1,32 +0,0 @@
-{
-  "_class_name": "StableDiffusionPipeline",
-  "_diffusers_version": "0.8.0.dev0",
-  "feature_extractor": [
-    "transformers",
-    "CLIPFeatureExtractor"
-  ],
-  "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
-  ],
-  "scheduler": [
-    "diffusers",
-    "PNDMScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}

safety_checker/config.json

@@ -1,179 +0,0 @@
-{
-  "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
-  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
-  "architectures": [
-    "StableDiffusionSafetyChecker"
-  ],
-  "initializer_factor": 1.0,
-  "logit_scale_init_value": 2.6592,
-  "model_type": "clip",
-  "projection_dim": 768,
-  "text_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 77,
-    "min_length": 0,
-    "model_type": "clip_text_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_hidden_layers": 12,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": 1,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.24.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "vocab_size": 49408
-  },
-  "text_config_dict": {
-    "hidden_size": 768,
-    "intermediate_size": 3072,
-    "num_attention_heads": 12,
-    "num_hidden_layers": 12
-  },
-  "torch_dtype": "float32",
-  "transformers_version": null,
-  "vision_config": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 224,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 4096,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layer_norm_eps": 1e-05,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "clip_vision_model",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
-    "num_channels": 3,
-    "num_hidden_layers": 24,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.24.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "vision_config_dict": {
-    "hidden_size": 1024,
-    "intermediate_size": 4096,
-    "num_attention_heads": 16,
-    "num_hidden_layers": 24,
-    "patch_size": 14
-  }
-}

scheduler/scheduler_config.json

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

text_encoder/config.json

@@ -1,25 +0,0 @@
-{
-  "_name_or_path": "openai/clip-vit-large-patch14",
-  "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
-}

tokenizer/special_tokens_map.json

@@ -1,24 +0,0 @@
-{
-  "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

@@ -1,34 +0,0 @@
-{
-  "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": "openai/clip-vit-large-patch14",
-  "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

@@ -1,36 +0,0 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.8.0.dev0",
-  "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"
-  ]
-}

vae/config.json

@@ -1,29 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.8.0.dev0",
-  "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": 256,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}