Update README.md

Browse files

Files changed (1) hide show

README.md +190 -152

README.md CHANGED Viewed

@@ -1,212 +1,250 @@
 ---
-pipeline_tag: text-to-image
-tags:
-  - text-to-image
-  - image-generation
-  - diffusion-transformer
-  - dit
-  - comfyui
-  - checkpoint
-  - safetensors
-  - aio
-  - all-in-one
-  - ernie-image
-  - ernie-image-turbo
-  - bf16
-  - fp8
-license: apache-2.0
-widget:
-  - text: "A premium sci-fi poster with readable text, cinematic lighting, and a futuristic city skyline at night."
-  - text: "A clean product advertisement for a coffee brand with readable package text, elegant layout, and warm morning light."
 ---
-# ERNIE AIO for ComfyUI
-**All-in-One Checkpoints • Base + Turbo • BF16 & FP8 • Integrated Text Encoder + VAE**
-This repository provides **AIO (All-in-One)** checkpoint versions of **ERNIE-Image** and **ERNIE-Image-Turbo** for **ComfyUI**.
-A ready-to-use **ComfyUI workflow** is included in the **`Workflow/`** folder, and the optional **Prompt Enhancer** files are included in the **`prompt-enhancer/`** folder.
-These AIO releases are designed for users who prefer a classic **single-checkpoint workflow**.
-Each checkpoint already contains the **image model**, **text encoder**, and **VAE**, so no separate text encoder or VAE loading is required.
-### ERNIE-AIO-Base
-![ERNIE-AIO-Base preview](./images/ernie-aio-base.png)
-### ERNIE-AIO-Turbo
-![ERNIE-AIO-Turbo preview](./images/ernie-aio-turbo.png)
-## Overview
-This repository provides **AIO (All-in-One)** checkpoint versions of **ERNIE-Image** and **ERNIE-Image-Turbo** for **ComfyUI**.
-These AIO releases are designed for users who prefer a classic **single-checkpoint workflow**.
-Each checkpoint already contains the **image model**, **text encoder**, and **VAE**, so no separate text encoder or VAE loading is required.
-## Available Files
-### Main checkpoints
-- `ERNIE-AIO-Base-bf16.safetensors`
-- `ERNIE-AIO-Base-fp8.safetensors`
-- `ERNIE-AIO-Turbo-bf16.safetensors`
-- `ERNIE-AIO-Turbo-fp8.safetensors`
-### Workflow
-- `Workflow/ERNIE-AIO-Upscale.json`
-### Prompt Enhancer
-- `prompt-enhancer/` contains the optional ERNIE Prompt Enhancer files used by the workflow
-## What “AIO” means here
-The AIO checkpoints are packaged so they can be placed directly in:
-`ComfyUI/models/checkpoints`
-and loaded with the normal **Checkpoint Loader** node in ComfyUI.
-This means you can use a very small workflow such as:
-1. **Checkpoint Loader**
-2. **CLIP Text Encode (Prompt)**
-3. **Empty Latent Image**
-4. **KSampler**
-5. **VAE Decode**
-6. **Save Image**
-A workflow file may also be included separately for convenience.
-## Model Background
-These AIO releases are based on Baidu’s official **ERNIE-Image** family.
-According to the official model pages:
-- **ERNIE-Image** is an open text-to-image model built on a **single-stream Diffusion Transformer (DiT)** and paired with a lightweight **Prompt Enhancer**
-- **ERNIE-Image-Turbo** is the **distilled** variant, designed for strong fidelity in only **8 inference steps**
-- The official releases emphasize **instruction following**, **text rendering**, and **structured image generation**, making them especially interesting for posters, comics, infographics, UI-like layouts, and other text-heavy or layout-sensitive images
-## AIO Variants
-### ERNIE-AIO-Base
-The Base version is intended for more deliberate, stable, and higher-quality generation.
-**Recommended settings:**
-- **Steps:** 50
-- **CFG:** 4.0
-Use this version when you want stronger refinement, more careful rendering, and the full non-turbo experience.
-### ERNIE-AIO-Turbo
-The Turbo version is intended for fast generation and quick iteration.
-**Recommended settings:**
-- **Steps:** 8
-- **CFG:** 1.0
-Use this version when you want faster turnaround while still keeping good prompt fidelity and strong visual output.
-## Precision / Quantization Notes
-The **FP8** versions in this repository were quantized by me.
-For these FP8 AIO checkpoints:
-- **Image model:** FP8
-- **Text encoder:** FP8
-- **VAE:** FP32
-This setup was chosen to reduce size and improve practicality while keeping decoding stable.
-## Prompt Enhancer
-This repository also includes an optional **Prompt Enhancer** in the `text encoder/` folder.
-It can be used with the included workflow to automatically expand short prompts into richer and more descriptive prompts.
-This is optional, but useful if you want more detailed prompt wording or a more guided workflow experience.
-## Prompting
-These models work well with **natural language prompts**.
-They are especially suitable for:
-- posters
-- title cards
-- product ads
-- readable text in images
-- structured layouts
-- comics
-- infographics
-- UI-like visuals
-- realistic and stylized imagery
-For best results, describe:
-- subject
-- environment
-- composition
-- mood
-- lighting
-- camera framing
-- text that should appear in the image
-## Example Prompt Ideas
-- A cinematic movie poster with a bold readable title at the top, dramatic lighting, and a futuristic skyline.
-- A modern coffee advertisement with readable packaging text and a premium warm studio look.
-- A clean infographic with clearly labeled sections and a structured layout.
-- A comic-style scene with readable speech bubbles and strong composition.
-## ComfyUI Usage
-Place the checkpoints in:
-`ComfyUI/models/checkpoints`
-Then load them through **Checkpoint Loader** like a normal checkpoint.
-No separate:
-- VAE loader
-- text encoder loader
-- extra model assembly
-is required for the AIO versions.
-## Repository Structure
-- Main AIO checkpoints for **ERNIE-AIO-Base** and **ERNIE-AIO-Turbo**
-- `Workflow/` contains the ready-to-use ComfyUI workflow JSON
-- `prompt-enhancer/` contains the optional Prompt Enhancer files used by the workflow
-- `images/` contains the preview / title images for the Base and Turbo releases
-## Civitai Releases
-If you prefer the Civitai pages, you can also find the releases here:
-- Turbo: https://civitai.red/models/2551548?modelVersionId=2868512
-- Base: https://civitai.red/models/2551548?modelVersionId=2867462
-## Limitations
-As with other image generation models:
-- text rendering can still vary depending on prompt complexity
-- highly dense typography may require retries
-- prompt phrasing can strongly affect layout quality
-- FP8 variants may behave slightly differently from BF16 variants depending on hardware and workflow
-## Intended Use
-These releases are intended for:
-- local image generation in ComfyUI
-- poster and design-style generation
-- readable title images
-- structured compositions
-- users who want a simple all-in-one checkpoint workflow
-## Credits
-Huge thanks to the original **ERNIE-Image** team at **Baidu** for releasing the official models.
-Official sources:
-- **ERNIE-Image:** https://huggingface.co/baidu/ERNIE-Image
-- **ERNIE-Image-Turbo:** https://huggingface.co/baidu/ERNIE-Image-Turbo
-- **GitHub:** https://github.com/baidu/ERNIE-Image
-## License
-This repository is based on the official ERNIE-Image releases, whose Hugging Face model pages list the license as **Apache-2.0**.
-## Final Note
-These AIO releases were made to simplify the ERNIE workflow for ComfyUI users.
-Load checkpoint, write prompt, sample, decode, save.

+---
+pipeline_tag: text-to-image
+tags:
+- text-to-image
+- image-generation
+- diffusion-transformer
+- dit
+- comfyui
+- checkpoint
+- safetensors
+- aio
+- all-in-one
+- ernie-image
+- ernie-image-turbo
+- bf16
+- fp8
+license: apache-2.0
+widget:
+- text: >-
+    A premium sci-fi poster with readable text, cinematic lighting, and a
+    futuristic city skyline at night.
+- text: >-
+    A clean product advertisement for a coffee brand with readable package text,
+    elegant layout, and warm morning light.
+language:
+- en
+---
+# 🖼️ ERNIE AIO for ComfyUI
+**All-in-One Checkpoints • Base + Turbo • BF16 & FP8 • Text Encoder + VAE Included**
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![ComfyUI](https://img.shields.io/badge/ComfyUI-Compatible-green.svg)](https://github.com/comfyanonymous/ComfyUI)
 ---
+- [📦 Models](#-models)
+- [📋 Workflow](#-workflow)
+- [📸 ERNIE-AIO-Base](#-ernie-aio-base)
+- [⚡ ERNIE-AIO-Turbo](#-ernie-aio-turbo)
+- [🔄 FP8 vs BF16](#-fp8-vs-bf16)
+- [⚙️ Common Settings](#️-common-settings)
+- [🗂️ Prompt Enhancer](#️-prompt-enhancer)
+- [💡 Prompting](#-prompting)
+- [📥 Downloads](#-downloads)
+- [📁 Files](#-files)
+- [🙏 Credits](#-credits)
 ---
+## 📦 Models
+| Model | Style | FP8 | BF16 | Best For |
+|---|---|---|---|---|
+| 📸 **ERNIE-AIO-Base** | Realistic / Structured | ✅ | ✅ | High-quality, refined output |
+| ⚡ **ERNIE-AIO-Turbo** | Realistic / Structured | ✅ | ✅ | Fast iteration, 8-step generation |
+**All models:** Integrated Text Encoder + VAE • Single Checkpoint • No extra loaders needed
+---
+## 📋 Workflow
+| File | Description |
+|---|---|
+| `Workflow/ERNIE-AIO-Upscale.json` | Standard ComfyUI workflow with upscaler |
+> ✅ A ready-to-use **ComfyUI workflow** is included in the `Workflow/` folder.
+> ✅ Optional **Prompt Enhancer** files are included in the `prompt-enhancer/` folder.
+---
+## 📸 ERNIE-AIO-Base
+The Base version is intended for high-quality, deliberate, and stable generation.
+**Features:** 📖 Strong instruction following • 🖋️ Text rendering • 📐 Structured layouts
+```
+Steps: 50  |  CFG: 4.0
+```
+[![ERNIE-AIO-Base preview](https://huggingface.co/SeeSee21/ERNIE-AIO/resolve/main/images/ernie-aio-base.png)](https://huggingface.co/SeeSee21/ERNIE-AIO/blob/main/images/ernie-aio-base.png)
+Use this version when you want:
+- Stronger refinement and more careful rendering
+- Full non-turbo quality
+- Best results for posters, infographics, and text-heavy layouts
+---
+## ⚡ ERNIE-AIO-Turbo
+The Turbo version is a distilled variant for fast generation and quick iteration.
+**Features:** ⚡ 8-step generation • 🎯 High prompt fidelity • 🚀 Quick turnaround
+```
+Steps: 8  |  CFG: 1.0
+```
+[![ERNIE-AIO-Turbo preview](https://huggingface.co/SeeSee21/ERNIE-AIO/resolve/main/images/ernie-aio-turbo.png)](https://huggingface.co/SeeSee21/ERNIE-AIO/blob/main/images/ernie-aio-turbo.png)
+Use this version when you want:
+- Fast output for prototyping and iteration
+- Strong visual quality with minimal steps
+- Efficient VRAM usage
+---
+## 🔄 FP8 vs BF16
+| | 🟡 FP8 | 🌟 BF16 |
+|---|---|---|
+| **Quality** | ~95% | 100% |
+| **File Size** | Smaller | Full |
+| **Speed** | Faster | Standard |
+| **VAE** | FP32 (stable) | FP32 (stable) |
+| **Best For** | Daily use | Final renders |
+> **Note:** The FP8 versions in this repository were quantized by me.
+> VAE is kept at **FP32** in all variants for stable decoding.
+---
+## ⚙️ Common Settings
+```
+# ERNIE-AIO-Base
+Steps:    50
+CFG:      4.0
+# ERNIE-AIO-Turbo
+Steps:    8
+CFG:      1.0
+# Placement (both variants)
+ComfyUI/models/checkpoints/
+# Loader
+Standard "Load Checkpoint" node — no extra VAE or text encoder loader needed
+```
+**Minimal workflow:**
+1. **Checkpoint Loader**
+2. **CLIP Text Encode (Prompt)**
+3. **Empty Latent Image**
+4. **KSampler**
+5. **VAE Decode**
+6. **Save Image**
+---
+## 🗂️ Prompt Enhancer
+An optional **Prompt Enhancer** is included in the `prompt-enhancer/` folder.
+- Automatically expands short prompts into richer, more descriptive prompts
+- Used by the included workflow
+- Fully optional — works without it too
+---
+## 💡 Prompting
+**Natural language works best!** These models excel at instruction following and text rendering.
+```
+✅ A cinematic movie poster with a bold readable title at the top,
+   dramatic lighting, a futuristic skyline in the background,
+   and a heroic figure silhouetted against a neon-lit city.
+❌ movie poster, city, hero, cinematic, dramatic
+```
+**ERNIE-Image is especially strong for:**
+| Category | Examples |
+|---|---|
+| 🎬 Posters & Title Cards | Movie posters, event flyers, title images |
+| ☕ Product Ads | Coffee brands, packaging with readable text |
+| 📊 Infographics | Labeled sections, structured layouts |
+| 💬 Comics | Speech bubbles, panel compositions |
+| 🖥️ UI-style Visuals | Interface mockups, app screens |
+| 🖼️ Realistic Imagery | Portraits, environments, product shots |
+**For best results, describe:**
+- Subject & environment
+- Composition & layout
+- Mood & lighting
+- Camera framing
+- Any text that should appear in the image
+---
+## 📥 Downloads
+### ERNIE-AIO Checkpoints
+| Model | Precision | CivitAI |
+|---|---|---|
+| ⚡ **ERNIE-AIO-Turbo** | 🌟 BF16 | [Download](https://civitai.red/models/2551548?modelVersionId=2868512) |
+| ⚡ **ERNIE-AIO-Turbo** | 🟡 FP8 | [Download](https://civitai.red/models/2551548?modelVersionId=2868512) |
+| 📸 **ERNIE-AIO-Base** | 🌟 BF16 | [Download](https://civitai.red/models/2551548?modelVersionId=2867462) |
+| 📸 **ERNIE-AIO-Base** | 🟡 FP8 | [Download](https://civitai.red/models/2551548?modelVersionId=2867462) |
+> All files are also available directly on this HuggingFace page.
+---
+## 📁 Files
+```
+├── ERNIE-AIO-Base-bf16.safetensors        # 📸 Base  — BF16
+├── ERNIE-AIO-Base-fp8.safetensors         # 📸 Base  — FP8
+├── ERNIE-AIO-Turbo-bf16.safetensors       # ⚡ Turbo — BF16
+├── ERNIE-AIO-Turbo-fp8.safetensors        # ⚡ Turbo — FP8
+│
+├── Workflow/
+│   └── ERNIE-AIO-Upscale.json             # 🚀 ComfyUI workflow with upscaler
+│
+├── prompt-enhancer/                        # 🗂️ Optional Prompt Enhancer files
+│
+└── images/
+    ├── ernie-aio-base.png                  # 📸 Base preview image
+    └── ernie-aio-turbo.png                 # ⚡ Turbo preview image
+```
+---
+## 🙏 Credits
+**Original Model:** Baidu ERNIE-Image Team • Single-Stream DiT • Apache 2.0
+**AIO Conversion & FP8 Quantization:** [SeeSee21](https://huggingface.co/SeeSee21)
+**Official Sources:**
+| Resource | Link |
+|---|---|
+| ERNIE-Image (HuggingFace) | [baidu/ERNIE-Image](https://huggingface.co/baidu/ERNIE-Image) |
+| ERNIE-Image-Turbo (HuggingFace) | [baidu/ERNIE-Image-Turbo](https://huggingface.co/baidu/ERNIE-Image-Turbo) |
+| GitHub | [baidu/ERNIE-Image](https://github.com/baidu/ERNIE-Image) |
+---
+**Download → Load Checkpoint → Generate!** 🚀
+**Place in `checkpoints/`, load with "Load Checkpoint", and generate in seconds!**