Upload 18 files

README.md

@@ -0,0 +1,71 @@
+---
+language:
+- en
+license: cc-by-nc-nd-4.0
+library_name: diffusers
+tags:
+- art
+- people
+- diffusion
+- Cinematic
+- Photography
+- Landscape
+- Interior
+- Food
+- Car
+- Wildlife
+- Architecture
+thumbnail: >-
+  https://storage.googleapis.com/run-diffusion-public-assets/juggernaut-xi/juggernaut-collage-256.webp
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+pipeline_tag: text-to-image
+---
+
+# Juggernaut XI v11 by RunDiffusion (Official)
+
+🎉 Juggernaut XI is Comming! 🌍
+The next version of Juggernaut is on the horizon. Follow our social media accounts to be notified when we launch.
+
+Juggernaut XI is available now on [RunDiffusion.com](http://rundiffusion.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=juggernautv11) and through an API on Octo.AI
+
+https://x.com/RunDiffusion & https://x.com/Juggernaut_AI
+
+**Terms and Conditions:**
+By providing your name and email, you consent to not use this model behind API's or generative services or on a competing platform or service to RunDiffusion.com. 
+Commercial licences can be obtained by emailing juggernaut@rundiffusion.com. You also agree to receive communications from RunDiffusion, including information on model releases, platform updates, and news from RunDiffusion.
+RunDiffusion values your privacy and will not misuse your information. We are committed to avoiding irrelevant or unsolicited messages.
+
+![juggernaut XI photo previews](https://storage.googleapis.com/run-diffusion-public-assets/juggernaut-xi/juggernaut-collage-832.webp)
+![RunDiffusion Logo](https://imagedelivery.net/siANnpeNAc_S2q1M3-eDrA/ca2b388d-a835-490c-dec0-e764bee8d000/micro)
+This model is not permitted to be used behind API services. Please contact [juggernaut@rundiffusion.com](mailto:juggernaut@rundiffusion.com) for business inquires, commercial licensing, custom models, and consultation.
+
+Over two months have passed and we are thrilled to announce the next version of Juggernaut!
+
+- Amazing prompt adherence ✅
+- Massively improved aesthetics
+- Better hands, eyes, faces, and compostion
+- Fully trained from the ground up using the GPT4 Vision Captioning tool by LEOSAM 🛠️
+- Expanded and cleaner dataset with higher quality images 🖼️
+- Improved classifications of shots (Full Body, Midshots, Portraits, etc) 📸
+- Enhanced text generation capability 📝
+- Two different prompting techniques, Natural and Tagging style 🏷️
+- Enhanced by RunDiffusion Photo for refinement of details 🧐
+
+Read more about this version here https://rundiffusion.com/juggernaut-xi
+
+Uset his now exclusively through Fooocus on RunDiffusion.com
+- Launch Fooocus on RunDiffusion
+- Find Juggernaut_XI_byRunDiffusion.safetensors and start generating!
+
+Prompting Guide 📘
+Because everything has been trained from the ground up, prompting is a bit different. (Simpler, don't worry) @Kandoo has created a guide to help you seamlessly integrate this powerful model into your workflow, enabling you to leverage its advanced capabilities without feeling overwhelmed. Download it here: https://rundiffusion.com/juggernaut-xl#nav
+
+As always, we love our community and feel so lucky to be in this position to bring these awesome tools and models to you amazing diffusers. Thanks for supporting us since our first day back in 2022. Going on TWO YEARS since we first started using generative Ai. Time flies when you're having fun. wow!
+
+Don't forget to follow us on Twitter where we have way more updates on big things we're working on. The future is bright
+
+https://x.com/RunDiffusion
+
+-RunDiffusion Team 
+
+![https://rundiffusion.com?utm_source=huggingface&utm_medium=referral&utm_campaign=juggernautv11](https://i.imgur.com/fKPEqSu.jpg)

model_index.json

@@ -1,42 +1,41 @@
-{
-  "_class_name": "StableDiffusionXLPipeline",
-  "_diffusers_version": "0.32.2",
-  "_name_or_path": "RunDiffusion/Juggernaut-XI-v11",
-  "feature_extractor": [
-    null,
-    null
-  ],
-  "force_zeros_for_empty_prompt": true,
-  "image_encoder": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "EulerDiscreteScheduler"
-  ],
-  "text_encoder": [
-    "transformers",
-    "CLIPTextModel"
-  ],
-  "text_encoder_2": [
-    "transformers",
-    "CLIPTextModelWithProjection"
-  ],
-  "tokenizer": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "tokenizer_2": [
-    "transformers",
-    "CLIPTokenizer"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.26.3",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -1,24 +1,21 @@
-{
-  "_class_name": "EulerDiscreteScheduler",
-  "_diffusers_version": "0.32.2",
-  "beta_end": 0.012,
-  "beta_schedule": "scaled_linear",
-  "beta_start": 0.00085,
-  "final_sigmas_type": "zero",
-  "interpolation_type": "linear",
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
-  "set_alpha_to_one": false,
-  "sigma_max": null,
-  "sigma_min": null,
-  "skip_prk_steps": true,
-  "steps_offset": 1,
-  "timestep_spacing": "leading",
-  "timestep_type": "discrete",
-  "trained_betas": null,
-  "use_beta_sigmas": false,
-  "use_exponential_sigmas": false,
-  "use_karras_sigmas": false
-}
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.26.3",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -1,25 +1,24 @@
-{
-  "_name_or_path": "/root/.cache/huggingface/hub/models--RunDiffusion--Juggernaut-XI-v11/snapshots/17a87abb089586ab38591a2309da18e44e2c8917/text_encoder",
-  "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": "float16",
-  "transformers_version": "4.48.2",
-  "vocab_size": 49408
-}
+{
+  "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": "4.30.2",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1126c5a4cfdced7ed962724ab0b72601aea66808cd55e12689e3185629f1ce
-size 246144152
+oid sha256:205903ff704616a765d9c5f7ad43d94fa5f76a1979c3e07370cbbb31b4e2d119
+size 492307041

text_encoder_2/config.json

@@ -1,25 +1,24 @@
-{
-  "_name_or_path": "/root/.cache/huggingface/hub/models--RunDiffusion--Juggernaut-XI-v11/snapshots/17a87abb089586ab38591a2309da18e44e2c8917/text_encoder_2",
-  "architectures": [
-    "CLIPTextModelWithProjection"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "dropout": 0.0,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_size": 1280,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 5120,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 77,
-  "model_type": "clip_text_model",
-  "num_attention_heads": 20,
-  "num_hidden_layers": 32,
-  "pad_token_id": 1,
-  "projection_dim": 1280,
-  "torch_dtype": "float16",
-  "transformers_version": "4.48.2",
-  "vocab_size": 49408
-}
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "vocab_size": 49408
+}

text_encoder_2/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fc294c5c672fad7391c20cf8bebf6900cd4687776879723e634da28c6cf7b06
-size 1389382176
+oid sha256:8789c738d9b7fb569baf95add70c6b7269cdeee67bd0c1056875c0ed43d69355
+size 2778810597

tokenizer/special_tokens_map.json

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

@@ -1,31 +1,33 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "49406": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49407": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": true,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 77,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<|endoftext|>"
-}
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "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,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/special_tokens_map.json

@@ -1,24 +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": "!",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
-}
+{
+  "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": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -1,39 +1,33 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "!",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49406": {
-      "content": "<|startoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "49407": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|startoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": true,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 77,
-  "pad_token": "!",
-  "tokenizer_class": "CLIPTokenizer",
-  "unk_token": "<|endoftext|>"
-}
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "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,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -1,73 +1,72 @@
-{
-  "_class_name": "UNet2DConditionModel",
-  "_diffusers_version": "0.32.2",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--RunDiffusion--Juggernaut-XI-v11/snapshots/17a87abb089586ab38591a2309da18e44e2c8917/unet",
-  "act_fn": "silu",
-  "addition_embed_type": "text_time",
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": 256,
-  "attention_head_dim": [
-    5,
-    10,
-    20
-  ],
-  "attention_type": "default",
-  "block_out_channels": [
-    320,
-    640,
-    1280
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 2048,
-  "cross_attention_norm": null,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dropout": 0.0,
-  "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 4,
-  "layers_per_block": 2,
-  "mid_block_only_cross_attention": null,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "out_channels": 4,
-  "projection_class_embeddings_input_dim": 2816,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
-  "resnet_time_scale_shift": "default",
-  "reverse_transformer_layers_per_block": null,
-  "sample_size": 128,
-  "time_cond_proj_dim": null,
-  "time_embedding_act_fn": null,
-  "time_embedding_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "transformer_layers_per_block": [
-    1,
-    2,
-    10
-  ],
-  "up_block_types": [
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "UpBlock2D"
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": true
-}
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.26.3",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": true
+}

vae/config.json

@@ -1,38 +1,31 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.32.2",
-  "_name_or_path": "/root/.cache/huggingface/hub/models--RunDiffusion--Juggernaut-XI-v11/snapshots/17a87abb089586ab38591a2309da18e44e2c8917/vae",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "force_upcast": true,
-  "in_channels": 3,
-  "latent_channels": 4,
-  "latents_mean": null,
-  "latents_std": null,
-  "layers_per_block": 2,
-  "mid_block_add_attention": true,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 1024,
-  "scaling_factor": 0.13025,
-  "shift_factor": null,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ],
-  "use_post_quant_conv": true,
-  "use_quant_conv": true
-}
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.26.3",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "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 sha256:37eb3e09ae1ce3d6891ddf809ca927b618e501091142cf07fdd9cd170e3a046f
+size 334712113