diff --git a/docs.json b/docs.json index 48cd6fc5e..c781ccaa4 100644 --- a/docs.json +++ b/docs.json @@ -112,6 +112,7 @@ { "group": "Flux", "pages": [ + "tutorials/flux/flux1-krea-dev", "tutorials/flux/flux-1-kontext-dev", "tutorials/flux/flux-1-text-to-image", "tutorials/flux/flux-1-fill-dev", @@ -656,6 +657,7 @@ { "group": "Flux", "pages": [ + "zh-CN/tutorials/flux/flux1-krea-dev", "zh-CN/tutorials/flux/flux-1-kontext-dev", "zh-CN/tutorials/flux/flux-1-text-to-image", "zh-CN/tutorials/flux/flux-1-fill-dev", diff --git a/images/tutorial/flux/flux_1_krea_dev_guide.jpg b/images/tutorial/flux/flux_1_krea_dev_guide.jpg new file mode 100644 index 000000000..d1bf9dae2 Binary files /dev/null and b/images/tutorial/flux/flux_1_krea_dev_guide.jpg differ diff --git a/images/tutorial/flux/flux_1_krea_dev_poster.jpg b/images/tutorial/flux/flux_1_krea_dev_poster.jpg new file mode 100644 index 000000000..cae91020b Binary files /dev/null and b/images/tutorial/flux/flux_1_krea_dev_poster.jpg differ diff --git a/snippets/tutorials/update-reminder.mdx b/snippets/tutorials/update-reminder.mdx index b286a6260..dc1b1c83b 100644 --- a/snippets/tutorials/update-reminder.mdx +++ b/snippets/tutorials/update-reminder.mdx @@ -1,4 +1,6 @@ +If you have not installed ComfyUI, please refer to the [ComfyUI System Requirements](/installation/system_requirements#system-requirements) section to install ComfyUI. + If you find missing nodes when loading the workflow file below, it may be due to the following situations: 1. You are not using the latest Development (Nightly) version of ComfyUI. diff --git a/snippets/zh/tutorials/update-reminder.mdx b/snippets/zh/tutorials/update-reminder.mdx index 9f950cc46..3b15a5673 100644 --- a/snippets/zh/tutorials/update-reminder.mdx +++ b/snippets/zh/tutorials/update-reminder.mdx @@ -1,4 +1,6 @@ +如果你未安装 ComfyUI 请参考[ComfyUI 系统要求说明](/zh-CN/installation/system_requirements#操作系统要求) 部分安装 ComfyUI。 + 如果在加载下面的工作流文件时，你发现存在节点缺失，可能是因为以下情况： 1. 你使用的 ComfyUI 版本不是最新的开发（nightly）版本。 diff --git a/tutorials/flux/flux1-krea-dev.mdx b/tutorials/flux/flux1-krea-dev.mdx new file mode 100644 index 000000000..f0af050cd --- /dev/null +++ b/tutorials/flux/flux1-krea-dev.mdx @@ -0,0 +1,87 @@ +--- +title: "Flux.1 Krea Dev ComfyUI Workflow Tutorial" +description: "Best open-source FLUX model developed by Black Forest Labs in collaboration with Krea, focusing on unique aesthetic style and natural details, avoiding AI look, providing exceptional realism and image quality." +sidebarTitle: "Flux.1 Krea Dev" +--- + +import UpdateReminder from '/snippets/en/tutorials/update-reminder.mdx' + +![Flux.1 Krea Dev Poster](/images/tutorial/flux/flux_1_krea_dev_poster.jpg) + +[Flux.1 Krea Dev](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev) is an advanced text-to-image generation model developed in collaboration between Black Forest Labs (BFL) and Krea. This is currently the best open-source FLUX model, specifically designed for text-to-image generation. + +**Model Features** + +- **Unique Aesthetic Style**: Focuses on generating images with unique aesthetics, avoiding common "AI look" appearance +- **Natural Details**: Does not produce blown-out highlights, maintaining natural detail representatio +- **Exceptional Realism**: Provides outstanding realism and image quality +- **Fully Compatible Architecture**: Fully compatible architecture design with FLUX.1 [dev] + +**Model License** +This model is released under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/blob/main/LICENSE.md) + +## Flux.1 Krea Dev ComfyUI Workflow + + + +#### 1. Workflow Files + +Download the image or JSON below and drag it into ComfyUI to load the corresponding workflow +![Flux Krea Dev Workflow](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/krea/flux1_krea_dev.png) + + +

Download JSON Workflow

+ + +#### 2. Manual Model Installation + +Please download the following model files: +**Diffusion model** + +- [flux1-krea-dev.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/resolve/main/flux1-krea-dev.safetensors) + +The `flux1-dev.safetensors` file requires agreeing to the [black-forest-labs/FLUX.1-Krea-dev](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/) agreement before downloading via browser. + + +If you have used Flux related workflows before, the following models are the same and don't need to be downloaded again + +**Text encoders** +- [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true) +- [t5xxl_fp16.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors?download=true) Recommended when your VRAM is greater than 32GB. +- [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors) For Low VRAM + +**VAE** +- [ae.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors?download=true) + +File save location: +``` +ComfyUI/ +├── models/ +│ ├── diffusion_models/ +│ │ └── flux1-krea-dev.safetensors +│ ├── text_encoders/ +│ │ ├── clip_l.safetensors +│ │ └── t5xxl_fp16.safetensors or t5xxl_fp8_e4m3fn.safetensors +│ ├── vae/ +│ │ └── ae.safetensors + +``` + +#### 3. Step-by-step Verification to Ensure Workflow Runs Properly + + + For low VRAM users, this model has nearly 47GB, so it may not run smoothly on your device, you can wait for the community to provide FP8 or GGUF version. + + +Please refer to the image below to ensure all model files have been loaded correctly + +![ComfyUI Flux Krea Dev Workflow](/images/tutorial/flux/flux_1_krea_dev_guide.jpg) + +1. Ensure that `flux1-krea-dev.safetensors` is loaded in the `Load Diffusion Model` node + - `weight_dtype` has been set to `fp8_e4m3fn_fast` for low VRAM users + - If you have sufficient VRAM like 24GB, you can set `weight_dtype` to `default` for better quality +2. Ensure the following models are loaded in the `DualCLIPLoader` node: + - clip_name1: t5xxl_fp16.safetensors or t5xxl_fp8_e4m3fn.safetensors + - clip_name2: clip_l.safetensors +3. Ensure that `ae.safetensors` is loaded in the `Load VAE` node +4. Click the `Queue` button, or use the shortcut `Ctrl(cmd) + Enter` to run the workflow \ No newline at end of file diff --git a/zh-CN/tutorials/flux/flux1-krea-dev.mdx b/zh-CN/tutorials/flux/flux1-krea-dev.mdx new file mode 100644 index 000000000..ede44b370 --- /dev/null +++ b/zh-CN/tutorials/flux/flux1-krea-dev.mdx @@ -0,0 +1,88 @@ +--- +title: "Flux.1 Krea Dev ComfyUI 工作流教程" +description: "Black Forest Labs 与 Krea 合作开发的最佳开源 FLUX 模型，专注于独特美学风格和自然细节，避免 AI 感，提供卓越的真实感和图像质量。" +sidebarTitle: "Flux.1 Krea Dev" +--- + +import UpdateReminder from '/snippets/zh/tutorials/update-reminder.mdx' + +![Flux.1 Krea Dev 海报](/images/tutorial/flux/flux_1_krea_dev_poster.jpg) + +[Flux.1 Krea Dev](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev) 是由 Black Forest Labs (BFL) 与 Krea 合作开发的先进文本生成图像模型。这是目前最好的开源权重 FLUX 模型，专为文本到图像生成而设计。 + +**模型特点** + +- **独特美学风格**: 专注于生成具有独特美学的图像，避免常见的"AI感"外观 +- **自然细节**: 不会产生过曝的高光，保持自然的细节表现 +- **卓越的真实感**: 提供出色的真实感和图像质量 +- **完全兼容架构**: 与 FLUX.1 [dev] 完全兼容的架构设计 + +**模型许可** +该模型采用 [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/blob/main/LICENSE.md) 许可发布 + +## Flux.1 Krea Dev ComfyUI 工作流 + + + +#### 1. 工作流文件 + +下载下面的图片或JSON，并拖入 ComfyUI 以加载对应工作流 +![Flux Krea Dev 工作流](https://raw.githubusercontent.com/Comfy-Org/example_workflows/main/flux/krea/flux1_krea_dev.png) + + +

下载 JSON 格式工作流

+ + +#### 2. 手动安装模型 + +请下载下面的模型文件： +**Diffusion model** + +- [flux1-krea-dev.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/resolve/main/flux1-krea-dev.safetensors) + +- `flux1-dev.safetensors` 文件需要同意 [black-forest-labs/FLUX.1-Krea-dev](https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev/) 的协议后才能使用浏览器进行下载。 + + +如果你使用过 Flux 相关的工作流，下面的模型是相同的，不需要重复下载 + +**Text encoders** +- [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true) +- [t5xxl_fp16.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors?download=true) 当你的显存大于 32GB 时推荐使用。 +- [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors) For Low VRAM + +**VAE** +- [ae.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors?download=true) + +文件保存位置： +``` +ComfyUI/ +├── models/ +│ ├── diffusion_models/ +│ │ └── flux1-krea-dev.safetensors +│ ├── text_encoders/ +│ │ ├── clip_l.safetensors +│ │ └── t5xxl_fp16.safetensors 或 t5xxl_fp8_e4m3fn.safetensors +│ ├── vae/ +│ │ └── ae.safetensors + +``` + +#### 3. 按步骤检查确保工作流可以正常运行 + + + 对于低显存用户， 这个模型有将近 47GB，所以可能无法在你的设备上顺利运行，你可以等待社区提供 FP8 或 GGUF 版本 + + +请参照下面的图片，确保各个模型文件都已经加载完成 + +![ComfyUI Flux Krea Dev工作流](/images/tutorial/flux/flux_1_krea_dev_guide.jpg) + +1. 确保在`Load Diffusion Model`节点加载了`flux1-krea-dev.safetensors` + - `weight_dtype`已为低显存用户设置成了 `fp8_e4m3fn_fast` + - 如果你有足够的显存如 24GB 可以将 `weight_dtype` 设置为 `default` 以获取更好的质量 +2. 确保在`DualCLIPLoader`节点中下面的模型已加载： + - clip_name1: t5xxl_fp16.safetensors 或 t5xxl_fp8_e4m3fn.safetensors + - clip_name2: clip_l.safetensors +3. 确保在`Load VAE`节点中加载了`ae.safetensors` +4. 确保 +4. 点击 `Queue` 按钮，或者使用快捷键 `Ctrl(cmd) + Enter(回车)` 来运行工作流 \ No newline at end of file