Text-to-Image
Diffusers
English
StableDiffusionXLPipeline
stable-diffusion
stable-diffusion-xl
sdxl
sdxl-lightning
photorealistic
fast
low-step
juggernaut
rundiffusion
kandooai
Instructions to use weiugh/Juggernaut-XL-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use weiugh/Juggernaut-XL-Lightning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("weiugh/Juggernaut-XL-Lightning", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit ·
1b21e25
0
Parent(s):
Duplicate from RunDiffusion/Juggernaut-XL-Lightning
Browse filesCo-authored-by: RunDiffusion <RunDiffusion@users.noreply.huggingface.co>
- .gitattributes +36 -0
- Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors +3 -0
- README.md +152 -0
- assets/Juggernaut_Banner.webp +3 -0
- model_index.json +41 -0
- scheduler/scheduler_config.json +21 -0
- text_encoder/config.json +24 -0
- text_encoder/pytorch_model.bin +3 -0
- text_encoder_2/config.json +24 -0
- text_encoder_2/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +33 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +24 -0
- tokenizer_2/tokenizer_config.json +33 -0
- tokenizer_2/vocab.json +0 -0
- unet/config.json +72 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +31 -0
- vae/diffusion_pytorch_model.bin +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
assets/Juggernaut_Banner.webp filter=lfs diff=lfs merge=lfs -text
|
Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8df560d2992ac04299412be6a36fa53a4e7a1b74f27b94867ad3f84f4b425a5
|
| 3 |
+
size 7105348284
|
README.md
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: creativeml-openrail-m
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: diffusers
|
| 6 |
+
pipeline_tag: text-to-image
|
| 7 |
+
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
| 8 |
+
tags:
|
| 9 |
+
- stable-diffusion
|
| 10 |
+
- stable-diffusion-xl
|
| 11 |
+
- sdxl
|
| 12 |
+
- sdxl-lightning
|
| 13 |
+
- text-to-image
|
| 14 |
+
- photorealistic
|
| 15 |
+
- fast
|
| 16 |
+
- low-step
|
| 17 |
+
- juggernaut
|
| 18 |
+
- rundiffusion
|
| 19 |
+
- kandooai
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
<div align="center">
|
| 23 |
+
|
| 24 |
+
<a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=header_banner">
|
| 25 |
+
<img src="https://huggingface.co/RunDiffusion/Juggernaut-XL-Lightning/resolve/main/assets/Juggernaut_Banner.webp" alt="Juggernaut — by RunDiffusion" />
|
| 26 |
+
</a>
|
| 27 |
+
|
| 28 |
+
<h1>Juggernaut XL Lightning by RunDiffusion</h1>
|
| 29 |
+
|
| 30 |
+
<p><i>Juggernaut quality at SDXL Lightning speed — 5–7 steps, photo-grade output.</i></p>
|
| 31 |
+
|
| 32 |
+
<p>
|
| 33 |
+
<a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=hero_cta"><img alt="Try Juggernaut Lightning — Free" src="https://img.shields.io/badge/%E2%96%B6%20Try%20Juggernaut%20Lightning%20%E2%80%94%20Free-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
|
| 34 |
+
</p>
|
| 35 |
+
|
| 36 |
+
<p>
|
| 37 |
+
<a href="https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&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> <a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&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> <img alt="5-7 steps" src="https://img.shields.io/badge/Inference-5%E2%80%937%20steps-EAB308?style=for-the-badge&labelColor=1f1f23"> <img alt="License: CreativeML Open RAIL-M" src="https://img.shields.io/badge/License-OpenRAIL--M-2ea44f?style=for-the-badge">
|
| 38 |
+
</p>
|
| 39 |
+
|
| 40 |
+
</div>
|
| 41 |
+
|
| 42 |
+
> Juggernaut XL Lightning is the **speed-optimized** member of the Juggernaut family — built on **SDXL Lightning** distillation, it produces photo-grade Juggernaut output in just **5–7 inference steps** instead of the usual 30–40. Same aesthetic, ~5× faster, ideal for batch generation, real-time iteration, and live demos.
|
| 43 |
+
|
| 44 |
+
## When to Use It
|
| 45 |
+
|
| 46 |
+
- ⚡ **Batch generation** — render hundreds of variations in the time you'd usually generate a few.
|
| 47 |
+
- 🔁 **Real-time iteration** — preview prompt changes in seconds, not minutes.
|
| 48 |
+
- 💻 **Lower-end hardware** — fewer steps means lower VRAM pressure during inference.
|
| 49 |
+
- 🎤 **Live demos and showcases** — instant turnaround when latency is the bottleneck.
|
| 50 |
+
|
| 51 |
+
If you need the very best per-image quality and don't mind the wait, use [**Juggernaut XL v9**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v9) instead — full-step inference holds slightly more detail.
|
| 52 |
+
|
| 53 |
+
---
|
| 54 |
+
|
| 55 |
+
<div align="center">
|
| 56 |
+
|
| 57 |
+
<h3>⚡ Want speed without setup? Run Lightning on RunDiffusion.</h3>
|
| 58 |
+
|
| 59 |
+
<p>Pre-loaded with the right scheduler, sampler, and CFG. <b>No installs. No GPU rental.</b></p>
|
| 60 |
+
|
| 61 |
+
<a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=midpage_cta"><img alt="Launch on RunDiffusion" src="https://img.shields.io/badge/%E2%96%B6%20Launch%20on%20RunDiffusion-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
|
| 62 |
+
|
| 63 |
+
<p><i>Pre-loaded into ComfyUI · Forge · Automatic1111 · Fooocus · InvokeAI · SwarmUI</i></p>
|
| 64 |
+
|
| 65 |
+
</div>
|
| 66 |
+
|
| 67 |
+
---
|
| 68 |
+
|
| 69 |
+
## Recommended Settings
|
| 70 |
+
|
| 71 |
+
> **These are different from standard Juggernaut.** Lightning needs fewer steps and lower CFG.
|
| 72 |
+
|
| 73 |
+
| Parameter | Value |
|
| 74 |
+
| --- | --- |
|
| 75 |
+
| Sampler | `DPM++ SDE` or `DPM++ SDE Karras` |
|
| 76 |
+
| Steps | `5 – 7` |
|
| 77 |
+
| CFG scale | `1.5 – 2.0` |
|
| 78 |
+
| Resolution | `≥ 1024 × 1024` (use SDXL-native sizes) |
|
| 79 |
+
| VAE | **Already baked in** — no external VAE required |
|
| 80 |
+
|
| 81 |
+
Standard Juggernaut prompts work as-is. Don't adjust your prompt for Lightning — just adjust the sampler, steps, and CFG.
|
| 82 |
+
|
| 83 |
+
📖 **Want to go deeper on prompting?** See the [**RunDiffusion prompting library**](https://www.rundiffusion.com/prompting?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=prompting_inline). Free to read, no signup.
|
| 84 |
+
|
| 85 |
+
## Two Ways to Run Juggernaut XL Lightning
|
| 86 |
+
|
| 87 |
+
### 🚀 Easiest — Run it on RunDiffusion (recommended)
|
| 88 |
+
|
| 89 |
+
One-click access inside ComfyUI, Forge, Automatic1111, Fooocus, InvokeAI, or SwarmUI. **Free trial included**, plus access to every other Juggernaut model on the same account.
|
| 90 |
+
|
| 91 |
+
<div align="center">
|
| 92 |
+
<a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&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>
|
| 93 |
+
</div>
|
| 94 |
+
|
| 95 |
+
### 💻 Or run it locally — Diffusers
|
| 96 |
+
|
| 97 |
+
```python
|
| 98 |
+
import torch
|
| 99 |
+
from diffusers import DiffusionPipeline, DPMSolverSinglestepScheduler
|
| 100 |
+
|
| 101 |
+
pipe = DiffusionPipeline.from_pretrained(
|
| 102 |
+
"RunDiffusion/Juggernaut-XL-Lightning",
|
| 103 |
+
torch_dtype=torch.float16,
|
| 104 |
+
use_safetensors=True,
|
| 105 |
+
).to("cuda")
|
| 106 |
+
|
| 107 |
+
# DPM++ SDE Karras
|
| 108 |
+
pipe.scheduler = DPMSolverSinglestepScheduler.from_config(
|
| 109 |
+
pipe.scheduler.config, use_karras_sigmas=True
|
| 110 |
+
)
|
| 111 |
+
|
| 112 |
+
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"
|
| 113 |
+
|
| 114 |
+
image = pipe(prompt, width=1024, height=1024, num_inference_steps=6, guidance_scale=1.8).images[0]
|
| 115 |
+
image.save("juggernaut_xl_lightning.png")
|
| 116 |
+
```
|
| 117 |
+
|
| 118 |
+
For ComfyUI / Forge / InvokeAI / SwarmUI: download the single-file checkpoint and drop it into your `models/checkpoints/` directory.
|
| 119 |
+
|
| 120 |
+
## The Rest of the Family
|
| 121 |
+
|
| 122 |
+
| Model | Best for |
|
| 123 |
+
| --- | --- |
|
| 124 |
+
| [**Juggernaut XL v9**](https://huggingface.co/RunDiffusion/Juggernaut-XL-v9) | The flagship SDXL — full-step photorealism workhorse. **6M+ downloads.** |
|
| 125 |
+
| [**Juggernaut XI v11**](https://huggingface.co/RunDiffusion/Juggernaut-XI-v11) | Latest SDXL-line refinement |
|
| 126 |
+
| [**Juggernaut XI Lightning**](https://huggingface.co/RunDiffusion/Juggernaut-XI-Lightning) | Speed variant on the XI base |
|
| 127 |
+
| [**Juggernaut Z**](https://huggingface.co/RunDiffusion/Juggernaut-Z-Image) | Lumina-Image-2 architecture — cinematic, presentation-ready |
|
| 128 |
+
| [**Juggernaut Pro Flux**](https://www.rundiffusion.com/juggernaut-pro-flux?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=cross_promo_pro_flux) | FLUX.1 backbone — top-tier photo quality |
|
| 129 |
+
|
| 130 |
+
## Commercial Use
|
| 131 |
+
|
| 132 |
+
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)**.
|
| 133 |
+
|
| 134 |
+
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).
|
| 135 |
+
|
| 136 |
+
## Credits
|
| 137 |
+
|
| 138 |
+
Juggernaut XL Lightning 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_lightning&utm_content=credits)**, distilled on top of **[SDXL Lightning](https://huggingface.co/ByteDance/SDXL-Lightning)**.
|
| 139 |
+
|
| 140 |
+
---
|
| 141 |
+
|
| 142 |
+
<div align="center">
|
| 143 |
+
|
| 144 |
+
<h3>Ready to generate at speed?</h3>
|
| 145 |
+
|
| 146 |
+
<p>Juggernaut Lightning is one click away — no setup, no GPU rental, no model downloads.</p>
|
| 147 |
+
|
| 148 |
+
<a href="https://app.rundiffusion.com/login?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&utm_content=footer_cta"><img alt="Try Juggernaut Lightning — Free" src="https://img.shields.io/badge/%E2%96%B6%20Try%20Juggernaut%20Lightning%20%E2%80%94%20Free-7C3AED?style=for-the-badge&labelColor=7C3AED"></a>
|
| 149 |
+
|
| 150 |
+
<p><sub><a href="https://www.rundiffusion.com/juggernaut?utm_source=huggingface&utm_medium=model_card&utm_campaign=juggernaut_xl_lightning&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_lightning&utm_content=footer_prompting">Prompting guides</a> · <a href="mailto:juggernaut@rundiffusion.com">Commercial licensing</a></sub></p>
|
| 151 |
+
|
| 152 |
+
</div>
|
assets/Juggernaut_Banner.webp
ADDED
|
Git LFS Details
|
model_index.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "StableDiffusionXLPipeline",
|
| 3 |
+
"_diffusers_version": "0.26.3",
|
| 4 |
+
"feature_extractor": [
|
| 5 |
+
null,
|
| 6 |
+
null
|
| 7 |
+
],
|
| 8 |
+
"force_zeros_for_empty_prompt": true,
|
| 9 |
+
"image_encoder": [
|
| 10 |
+
null,
|
| 11 |
+
null
|
| 12 |
+
],
|
| 13 |
+
"scheduler": [
|
| 14 |
+
"diffusers",
|
| 15 |
+
"EulerDiscreteScheduler"
|
| 16 |
+
],
|
| 17 |
+
"text_encoder": [
|
| 18 |
+
"transformers",
|
| 19 |
+
"CLIPTextModel"
|
| 20 |
+
],
|
| 21 |
+
"text_encoder_2": [
|
| 22 |
+
"transformers",
|
| 23 |
+
"CLIPTextModelWithProjection"
|
| 24 |
+
],
|
| 25 |
+
"tokenizer": [
|
| 26 |
+
"transformers",
|
| 27 |
+
"CLIPTokenizer"
|
| 28 |
+
],
|
| 29 |
+
"tokenizer_2": [
|
| 30 |
+
"transformers",
|
| 31 |
+
"CLIPTokenizer"
|
| 32 |
+
],
|
| 33 |
+
"unet": [
|
| 34 |
+
"diffusers",
|
| 35 |
+
"UNet2DConditionModel"
|
| 36 |
+
],
|
| 37 |
+
"vae": [
|
| 38 |
+
"diffusers",
|
| 39 |
+
"AutoencoderKL"
|
| 40 |
+
]
|
| 41 |
+
}
|
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "EulerDiscreteScheduler",
|
| 3 |
+
"_diffusers_version": "0.26.3",
|
| 4 |
+
"beta_end": 0.012,
|
| 5 |
+
"beta_schedule": "scaled_linear",
|
| 6 |
+
"beta_start": 0.00085,
|
| 7 |
+
"interpolation_type": "linear",
|
| 8 |
+
"num_train_timesteps": 1000,
|
| 9 |
+
"prediction_type": "epsilon",
|
| 10 |
+
"rescale_betas_zero_snr": false,
|
| 11 |
+
"sample_max_value": 1.0,
|
| 12 |
+
"set_alpha_to_one": false,
|
| 13 |
+
"sigma_max": null,
|
| 14 |
+
"sigma_min": null,
|
| 15 |
+
"skip_prk_steps": true,
|
| 16 |
+
"steps_offset": 1,
|
| 17 |
+
"timestep_spacing": "leading",
|
| 18 |
+
"timestep_type": "discrete",
|
| 19 |
+
"trained_betas": null,
|
| 20 |
+
"use_karras_sigmas": false
|
| 21 |
+
}
|
text_encoder/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "quick_gelu",
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 77,
|
| 16 |
+
"model_type": "clip_text_model",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"projection_dim": 768,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.30.2",
|
| 23 |
+
"vocab_size": 49408
|
| 24 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:233b85970f2251a71412068deace755b1a51796afffe7b33977e33d012765661
|
| 3 |
+
size 492307041
|
text_encoder_2/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"CLIPTextModelWithProjection"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dropout": 0.0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_size": 1280,
|
| 11 |
+
"initializer_factor": 1.0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 5120,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 77,
|
| 16 |
+
"model_type": "clip_text_model",
|
| 17 |
+
"num_attention_heads": 20,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"projection_dim": 1280,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.30.2",
|
| 23 |
+
"vocab_size": 49408
|
| 24 |
+
}
|
text_encoder_2/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2f356e4c52bb60207743cdeb8f47d52c21b74240db57d5607943cf8095ef267
|
| 3 |
+
size 2778810597
|
tokenizer/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"clean_up_tokenization_spaces": true,
|
| 12 |
+
"do_lower_case": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 77,
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_2/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "!",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<|startoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"clean_up_tokenization_spaces": true,
|
| 12 |
+
"do_lower_case": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 77,
|
| 23 |
+
"pad_token": "!",
|
| 24 |
+
"tokenizer_class": "CLIPTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
tokenizer_2/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
unet/config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.26.3",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"addition_embed_type": "text_time",
|
| 6 |
+
"addition_embed_type_num_heads": 64,
|
| 7 |
+
"addition_time_embed_dim": 256,
|
| 8 |
+
"attention_head_dim": [
|
| 9 |
+
5,
|
| 10 |
+
10,
|
| 11 |
+
20
|
| 12 |
+
],
|
| 13 |
+
"attention_type": "default",
|
| 14 |
+
"block_out_channels": [
|
| 15 |
+
320,
|
| 16 |
+
640,
|
| 17 |
+
1280
|
| 18 |
+
],
|
| 19 |
+
"center_input_sample": false,
|
| 20 |
+
"class_embed_type": null,
|
| 21 |
+
"class_embeddings_concat": false,
|
| 22 |
+
"conv_in_kernel": 3,
|
| 23 |
+
"conv_out_kernel": 3,
|
| 24 |
+
"cross_attention_dim": 2048,
|
| 25 |
+
"cross_attention_norm": null,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"DownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D"
|
| 30 |
+
],
|
| 31 |
+
"downsample_padding": 1,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dual_cross_attention": false,
|
| 34 |
+
"encoder_hid_dim": null,
|
| 35 |
+
"encoder_hid_dim_type": null,
|
| 36 |
+
"flip_sin_to_cos": true,
|
| 37 |
+
"freq_shift": 0,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_only_cross_attention": null,
|
| 41 |
+
"mid_block_scale_factor": 1,
|
| 42 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 43 |
+
"norm_eps": 1e-05,
|
| 44 |
+
"norm_num_groups": 32,
|
| 45 |
+
"num_attention_heads": null,
|
| 46 |
+
"num_class_embeds": null,
|
| 47 |
+
"only_cross_attention": false,
|
| 48 |
+
"out_channels": 4,
|
| 49 |
+
"projection_class_embeddings_input_dim": 2816,
|
| 50 |
+
"resnet_out_scale_factor": 1.0,
|
| 51 |
+
"resnet_skip_time_act": false,
|
| 52 |
+
"resnet_time_scale_shift": "default",
|
| 53 |
+
"reverse_transformer_layers_per_block": null,
|
| 54 |
+
"sample_size": 128,
|
| 55 |
+
"time_cond_proj_dim": null,
|
| 56 |
+
"time_embedding_act_fn": null,
|
| 57 |
+
"time_embedding_dim": null,
|
| 58 |
+
"time_embedding_type": "positional",
|
| 59 |
+
"timestep_post_act": null,
|
| 60 |
+
"transformer_layers_per_block": [
|
| 61 |
+
1,
|
| 62 |
+
2,
|
| 63 |
+
10
|
| 64 |
+
],
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"CrossAttnUpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"UpBlock2D"
|
| 69 |
+
],
|
| 70 |
+
"upcast_attention": false,
|
| 71 |
+
"use_linear_projection": true
|
| 72 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bf0cf06bea161595e98cdfe2cdf51a96b03768b4483746151aaa1805298f700
|
| 3 |
+
size 10270603837
|
vae/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "AutoencoderKL",
|
| 3 |
+
"_diffusers_version": "0.26.3",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"block_out_channels": [
|
| 6 |
+
128,
|
| 7 |
+
256,
|
| 8 |
+
512,
|
| 9 |
+
512
|
| 10 |
+
],
|
| 11 |
+
"down_block_types": [
|
| 12 |
+
"DownEncoderBlock2D",
|
| 13 |
+
"DownEncoderBlock2D",
|
| 14 |
+
"DownEncoderBlock2D",
|
| 15 |
+
"DownEncoderBlock2D"
|
| 16 |
+
],
|
| 17 |
+
"force_upcast": true,
|
| 18 |
+
"in_channels": 3,
|
| 19 |
+
"latent_channels": 4,
|
| 20 |
+
"layers_per_block": 2,
|
| 21 |
+
"norm_num_groups": 32,
|
| 22 |
+
"out_channels": 3,
|
| 23 |
+
"sample_size": 1024,
|
| 24 |
+
"scaling_factor": 0.13025,
|
| 25 |
+
"up_block_types": [
|
| 26 |
+
"UpDecoderBlock2D",
|
| 27 |
+
"UpDecoderBlock2D",
|
| 28 |
+
"UpDecoderBlock2D",
|
| 29 |
+
"UpDecoderBlock2D"
|
| 30 |
+
]
|
| 31 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37eb3e09ae1ce3d6891ddf809ca927b618e501091142cf07fdd9cd170e3a046f
|
| 3 |
+
size 334712113
|