hofixD
/

comfyui-hidream-l1-full-img2img

Image-to-Image

Model card Files Files and versions Community

hofixD commited on Apr 24

Commit

6963cdc

verified ·

1 Parent(s): 5db4208

Update README.md

Browse files

Files changed (1) hide show

README.md +86 -53

README.md CHANGED Viewed

@@ -6,76 +6,109 @@ base_model:
 pipeline_tag: image-to-image
 ---
-# HiDream Img2Img ComfyUI Workflow
-This workflow enables advanced image-to-image generation using the HiDream model suite and Florence-2 prompt generator, designed for use with ComfyUI and Replicate.
-You can test this workflow directly on Replicate: [https://replicate.com/goodguy1963/hidream-l1-full-img2img](https://replicate.com/goodguy1963/hidream-l1-full-img2img)
-## Overview
-- **Image-to-image generation** with HiDream diffusion model
-- **Florence-2** for prompt generation and captioning
-- **VAE encoding/decoding** and advanced CLIP-based text encoding
-- **Negative prompt** support for artifact reduction
-- **LOW VRAM MODE**
-## Required Models & Credits
-### Diffusion Model
-- **hidream_i1_full_fp16.safetensors**
-  Place in: `ComfyUI/models/diffusion_models`
-  [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/diffusion_models/hidream_i1_full_fp16.safetensors)
-  **Thanks to [HiDream.ai](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI) for the model!**
-## For low VRAM user - GPU with less than 24GB VRAM:
-- You can replace the standard Diffusion Model Loader with the custom node **Unet LOADER** from [city96/ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) by city96.
-- Download the HiDream-I1 Full GGUF model from: [https://huggingface.co/city96/HiDream-I1-Full-gguf/tree/main](https://huggingface.co/city96/HiDream-I1-Full-gguf/tree/main)
-Place all in: ComfyUI/models/unet
-### Text Encoders
-Place all in: `ComfyUI/models/text_encoders`
-- **clip_g_hidream.safetensors**
-  [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/clip_g_hidream.safetensors)
-- **clip_l_hidream.safetensors**
-  [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/clip_l_hidream.safetensors)
-- **llama_3.1_8b_instruct_fp8_scaled.safetensors**
-  [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/llama_3.1_8b_instruct_fp8_scaled.safetensors)
-- **t5xxl_fp8_e4m3fn_scaled.safetensors**
-  [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/t5xxl_fp8_e4m3fn_scaled.safetensors)
-### VAE
-- **ae.safetensors**
-  Place in: `ComfyUI/models/vae`
-  [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/vae/ae.safetensors)
-### Florence-2 Prompt Generator (NO need to download - will be downloaded automatacally at runtime)
 - **Florence-2-large**
-  [Microsoft Florence-2](https://huggingface.co/microsoft/Florence-2-large)
-  **Thanks to [MiaoshouAI](https://huggingface.co/MiaoshouAI/Florence-2-large-PromptGen-v2.0) for the correct implementation!**
-## Usage
-1. Download all required models and place them in the correct directories as listed above.
-2. Drag the workflow image in ComfyUI
-3. Use the workflow to generate new images from your input images and prompts.
----
-## For low VRAM user - GPU with less than 24GB VRAM:
-- You can replace the standard Diffusion Model Loader with the custom node **Unet LOADER** from [city96/ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) by city96.
-- Download the HiDream-I1 Full GGUF model from: [https://huggingface.co/city96/HiDream-I1-Full-gguf/tree/main](https://huggingface.co/city96/HiDream-I1-Full-gguf/tree/main)
-- Follow the instructions in the custom node repository to set up and use the GGUF model with the Unet LOADER node.
-## Workflow Diagram
-See the full workflow structure here:
-[WORKFLOW-HIDREAM-IMG2IMG.png](https://huggingface.co/hofixD/comfyui-hidream-l1-full-img2img/blob/main/WORKFLOW-HIDREAM-IMG2IMG.png)
-## Acknowledgements
-- **HiDream.ai** for the diffusion model and encoders
-- **Microsoft** for Florence-2
 - **MiaoshouAI** for the Florence-2 prompt generator implementation
-- **ComfyUI** team for the UI and workflow engine
-Thank you to all model creators and contributors!

 pipeline_tag: image-to-image
 ---
+<div align="center">
+# 🌟 HiDream Img2Img ComfyUI Workflow
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-Models-blue)](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI)
+[![Replicate](https://img.shields.io/badge/Replicate-Demo-brightgreen)](https://replicate.com/goodguy1963/hidream-l1-full-img2img)
+#### Advanced image-to-image generation with HiDream model suite and Florence-2 prompt generator
+</div>
+## 📋 Overview
+This workflow combines the power of HiDream diffusion models with Florence-2 captioning for enhanced image-to-image generation in ComfyUI:
+- ✨ **Image-to-image generation** with the state-of-the-art HiDream diffusion model
+- 🔮 **Florence-2** intelligent prompt generation and image captioning
+- 🖼️ **VAE encoding/decoding** and advanced CLIP-based text encoding
+- 🚫 **Negative prompt** support for artifact reduction
+- 💻 **Low VRAM mode** available for systems with limited resources
+## 🚀 Try It Now!
+You can test this workflow directly on Replicate:
+[▶️ Run on Replicate](https://replicate.com/goodguy1963/hidream-l1-full-img2img)
+## 📥 Required Models & Setup
+### 🎨 Diffusion Model
+- **`hidream_i1_full_fp16.safetensors`**
+  📁 Place in: `ComfyUI/models/diffusion_models`
+  📦 [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/diffusion_models/hidream_i1_full_fp16.safetensors)
+  > **Credit:** [HiDream.ai](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI)
+### 📝 Text Encoders
+📁 Place all in: `ComfyUI/models/text_encoders`
+- **`clip_g_hidream.safetensors`**
+  📦 [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/clip_g_hidream.safetensors)
+- **`clip_l_hidream.safetensors`**
+  📦 [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/clip_l_hidream.safetensors)
+- **`llama_3.1_8b_instruct_fp8_scaled.safetensors`**
+  📦 [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/llama_3.1_8b_instruct_fp8_scaled.safetensors)
+- **`t5xxl_fp8_e4m3fn_scaled.safetensors`**
+  📦 [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/text_encoders/t5xxl_fp8_e4m3fn_scaled.safetensors)
+### 🖼️ VAE
+- **`ae.safetensors`**
+  📁 Place in: `ComfyUI/models/vae`
+  📦 [Download](https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/blob/main/split_files/vae/ae.safetensors)
+### 🔍 Florence-2 Prompt Generator
 - **Florence-2-large**
+  ⚡ Automatic download at runtime
+  📦 [Microsoft Florence-2](https://huggingface.co/microsoft/Florence-2-large)
+  > **Credit:** [MiaoshouAI](https://huggingface.co/MiaoshouAI/Florence-2-large-PromptGen-v2.0) for the optimized implementation
+## 💡 Usage Guide
+1. Download all required models and place them in the correct directories as listed above
+2. Import the workflow into ComfyUI
+3. Load your input image, adjust settings as needed
+4. Generate new images with enhanced quality
+## 💻 Low VRAM Mode (< 24GB VRAM)
+<div align="center">
+<img src="https://img.shields.io/badge/Memory-Efficient-brightgreen" alt="Memory Efficient"/>
+</div>
+For systems with limited VRAM, use this alternative setup:
+1. Install [city96/ComfyUI-GGUF](https://github.com/city96/ComfyUI-GGUF) custom node
+2. Replace the standard Diffusion Model Loader with the **Unet LOADER** node
+3. Download the optimized HiDream-I1 Full GGUF model:
+   - 📦 [HiDream-I1-Full-gguf](https://huggingface.co/city96/HiDream-I1-Full-gguf/tree/main)
+   - 📁 Place in: `ComfyUI/models/unet`
+## 📊 Workflow Diagram
+<div align="center">
+<img src="https://huggingface.co/hofixD/comfyui-hidream-l1-full-img2img/resolve/main/WORKFLOW-HIDREAM-IMG2IMG.png" alt="HiDream Workflow Diagram" width="85%"/>
+</div>
+## 🙏 Acknowledgements
+- **HiDream.ai** for the remarkable diffusion model and encoders
+- **Microsoft** for the Florence-2 vision-language model
 - **MiaoshouAI** for the Florence-2 prompt generator implementation
+- **ComfyUI** team for the intuitive workflow engine
+- **city96** for the GGUF optimization for low VRAM systems
+---
+<div align="center">
+<p>⭐ If you find this workflow useful, please consider starring the repository! ⭐</p>
+</div>