Duplicate from RunDiffusion/Juggernaut-XL-v9

Co-authored-by: RunDiffusion <RunDiffusion@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/Juggernaut_v9_banner.png filter=lfs diff=lfs merge=lfs -text
+assets/Juggernaut_v9_banner.webp filter=lfs diff=lfs merge=lfs -text

Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e3e68f89b8e38689e1097d4be4573cf308de4e3fd044c64ca697bdb4aa8bca
+size 7105348188

README.md

@@ -0,0 +1,185 @@
+---
+license: creativeml-openrail-m
+language:
+- en
+library_name: diffusers
+pipeline_tag: text-to-image
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+tags:
+- stable-diffusion
+- stable-diffusion-xl
+- sdxl
+- text-to-image
+- photorealistic
+- photography
+- cinematic
+- portrait
+- juggernaut
+- rundiffusion
+- kandooai
+---
+
+<div align="center">
+
+<a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=header_banner">
+  <img src="https://huggingface.co/RunDiffusion/Juggernaut-XL-v9/resolve/main/assets/Juggernaut_v9_banner.webp" alt="Juggernaut XL v9 — by RunDiffusion" />
+</a>
+
+<h1>Juggernaut XL v9 by RunDiffusion</h1>
+
+<p><i>The world's most-downloaded SDXL model — purpose-built for photorealism.</i></p>
+
+<p><b>6M+ downloads on Hugging Face · Overwhelmingly Positive on Civitai · 26 months in production</b></p>
+
+<p>
+  <a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=hero_cta"><img alt="Try Juggernaut XL v9 — Free" src="https://img.shields.io/badge/%E2%96%B6%20Try%20Juggernaut%20XL%20v9%20%E2%80%94%20Free-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
+</p>
+
+<p>
+  <a href="https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=prompting_resource"><img alt="Prompting Guides" src="https://img.shields.io/badge/%F0%9F%93%96%20Prompting%20Guides-1f1f23?style=for-the-badge"></a>&nbsp;<a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=lineup_compare"><img alt="Compare the Lineup" src="https://img.shields.io/badge/Compare%20the%20Lineup-1971c2?style=for-the-badge&labelColor=1f1f23"></a>&nbsp;<a href="https://civitai.com/models/133005/juggernaut-xl"><img alt="Civitai" src="https://img.shields.io/badge/Civitai-Overwhelmingly%20Positive-EAB308?style=for-the-badge&labelColor=1f1f23"></a>&nbsp;<img alt="License: CreativeML Open RAIL-M" src="https://img.shields.io/badge/License-OpenRAIL--M-2ea44f?style=for-the-badge">
+</p>
+
+</div>
+
+> Juggernaut XL is the most popular SDXL fine-tune in the world. Version 9 — co-developed by **KandooAI** and **RunDiffusion**, integrating **RunDiffusion Photo v2** — is the proven photorealism workhorse trusted by **hundreds of thousands of creators**: 6M+ all-time downloads on Hugging Face, 1.5M+ on Civitai, and an *Overwhelmingly Positive* rating across 7,780+ reviews.
+
+## Why Juggernaut XL v9 in 2026?
+
+The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint. Choose Juggernaut XL v9 when you want:
+
+- 📸 **Photorealism that holds up under scrutiny** — skin texture, micro-contrast, and natural lighting that translates from concept to print.
+- 💻 **Reasonable hardware** — runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB.
+- 🧰 **The full SDXL toolbox** — drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow.
+- 🏆 **Battle-tested reliability** — 26+ months in production, used in agencies, studios, and shipping products around the world.
+
+For experimental and frontier work, see the rest of the [Juggernaut family](#looking-for-something-newer). For SDXL photorealism, this is the king of the hill.
+
+---
+
+<div align="center">
+
+<h3>🚀 Skip the setup. Try Juggernaut XL v9 in your browser.</h3>
+
+<p>No installs. No GPU rental. No model downloads. <b>Just generate.</b></p>
+
+<a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=midpage_cta"><img alt="Launch Juggernaut on RunDiffusion" src="https://img.shields.io/badge/%E2%96%B6%20Launch%20on%20RunDiffusion-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
+
+<p><i>Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI</i></p>
+
+</div>
+
+---
+
+## What V9 Brought Over V8
+
+- **RunDiffusion Photo v2** integration — a substantial upgrade to the photographic backbone of the model
+- Improved **skin detail** and micro-texture rendering
+- Stronger **lighting** and **contrast** control
+- Better consistency across **portrait**, **architecture**, **automotive**, **wildlife**, **food**, **interior**, and **landscape** photography
+
+## Two Ways to Run Juggernaut XL v9
+
+### 🚀 Easiest — Run it on RunDiffusion (recommended)
+
+One-click access to Juggernaut XL v9 inside the UI you already know — ComfyUI, Forge, Automatic1111, Fooocus, InvokeAI, or SwarmUI. No setup, no model downloads, no GPU to rent. **Free trial included.**
+
+<div align="center">
+  <a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=quickstart_try"><img alt="Get Started Free" src="https://img.shields.io/badge/Get%20Started%20Free%20%E2%86%92-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
+</div>
+
+### 💻 Or run it locally — Diffusers
+
+```python
+import torch
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained(
+    "RunDiffusion/Juggernaut-XL-v9",
+    torch_dtype=torch.float16,
+    variant="fp16",
+    use_safetensors=True,
+).to("cuda")
+
+prompt = "Cinematic mid shot photo of an astronaut walking through a neon-lit Tokyo alley at night, hyperdetailed photography, skin details, shallow depth of field"
+
+image = pipe(
+    prompt,
+    width=832, height=1216,
+    num_inference_steps=35,
+    guidance_scale=5.0,
+).images[0]
+
+image.save("juggernaut_xl_v9.png")
+```
+
+For ComfyUI / Forge / InvokeAI / SwarmUI: download `Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors` and drop it into your `models/checkpoints/` directory.
+
+## Recommended Settings
+
+| Parameter | Value |
+| --- | --- |
+| Resolution | `832 × 1216` (portrait) · `1216 × 832` (landscape) |
+| Sampler | `DPM++ 2M Karras` |
+| Steps | `30 – 40` |
+| CFG scale | `3 – 7` (lower = more realistic) |
+| VAE | **Already baked in** — no external VAE required |
+| Hi-Res fix | `4xNMKD-Siax_200k` upscaler · 15 steps · 0.3 denoise · 1.5× upscale |
+
+> **Negative prompts:** start with **none**. Add specific things you don't want as you iterate. Heavy negatives often hurt more than they help on this model.
+
+### Useful Prompt Keywords
+
+These tokens reliably steer output:
+
+```
+Architecture Photography · Wildlife Photography · Car Photography
+Food Photography · Interior Photography · Landscape Photography
+Hyperdetailed Photography · Cinematic Movie · Still Mid Shot Photo
+Full Body Photo · Skin Details
+```
+
+📖 **For deeper prompting technique** — sampler choices, multi-subject framing, lighting language, negative-prompt strategy — see the [**RunDiffusion prompting library**](https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=prompting_inline). Free to read, no signup.
+
+## Files In This Repo
+
+| File | Purpose |
+| --- | --- |
+| `Juggernaut-XL_v9_RunDiffusionPhoto_v2.safetensors` | Single-file checkpoint for ComfyUI / Forge / InvokeAI / SwarmUI |
+| `unet/`, `text_encoder/`, `text_encoder_2/`, `vae/`, `tokenizer/`, `tokenizer_2/`, `scheduler/`, `model_index.json` | Diffusers-format directory tree (FP16 variant) for `from_pretrained` |
+
+## Looking For Something Newer?
+
+The Juggernaut family has continued to evolve. Match the model to your project:
+
+| Model | Architecture | Best for |
+| --- | --- | --- |
+| **[Juggernaut Z](https://huggingface.co/RunDiffusion/Juggernaut-Z-Image)** | Lumina-Image-2 | Cinematic, presentation-ready output with stronger lighting and atmosphere |
+| **[Juggernaut Pro Flux](https://www.rundiffusion.com/juggernaut-pro-flux?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=cross_promo_pro_flux)** | FLUX.1 | Highest photo quality with strong consistency and lower token cost |
+| **[Juggernaut XII / XIII Ragnarok](https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=cross_promo_family)** | SDXL | The latest evolutions of the SDXL line, refined for prompt adherence and realism |
+| **Juggernaut XL v9** *(this model)* | SDXL 1.0 | Proven SDXL photorealism workhorse with the broadest tooling ecosystem |
+
+All of them — and 100+ other SOTA models — are pre-loaded on **[RunDiffusion](https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=family_compare)**. Switch between them in two clicks.
+
+## Commercial Use
+
+This model **may not be deployed behind paid API services** without explicit licensing. For commercial licensing, custom models, business inquiries, or consultation, contact **[juggernaut@rundiffusion.com](mailto:juggernaut@rundiffusion.com)**.
+
+You are free to use this model for personal and creative work under the terms of the [CreativeML Open RAIL-M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license).
+
+## Credits
+
+Juggernaut XL v9 was created by **[KandooAI](https://twitter.com/Juggernaut_AI)** in collaboration with **[RunDiffusion](https://www.rundiffusion.com/?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=credits)**. The photographic backbone — **RunDiffusion Photo v2** — was developed by the RunDiffusion team. Thanks to **Adam Stewart** for prompting workflow.
+
+---
+
+<div align="center">
+
+<h3>Ready to generate?</h3>
+
+<p>Juggernaut XL v9 is one click away — no setup, no GPU rental, no model downloads.</p>
+
+<a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_cta"><img alt="Try Juggernaut XL v9 — Free" src="https://img.shields.io/badge/%E2%96%B6%20Try%20Juggernaut%20XL%20v9%20%E2%80%94%20Free-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
+
+<p><sub><a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_lineup">Compare the full Juggernaut lineup</a> · <a href="https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_v9&utm_content=footer_prompting">Prompting guides</a> · <a href="mailto:juggernaut@rundiffusion.com">Commercial licensing</a></sub></p>
+
+</div>

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.27.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "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

@@ -0,0 +1,18 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.24.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "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,
+  "skip_prk_steps": true,
+  "timestep_spacing": "trailing"
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "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": "4.38.0.dev0",
+  "vocab_size": 49408
+}

text_encoder/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698656aa4f452e1f8f38287240054a9b8d339b3051ec17d77d63bdb5605db01a
+size 246144152

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "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": "4.38.0.dev0",
+  "vocab_size": 49408
+}

text_encoder_2/model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9962c194f50a9c580ebe573f2a4756d76dcd29abe15bffb0a5905509eb6a8dda
+size 1389382176

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_2/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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "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
+}

unet/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1ee18eb36712683f50c1e674634875e2adf7413d7492d5f9aa7e69e1a8c17a
+size 5135149760

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.27.0.dev0",
+  "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.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342