logo
RunComfy
ComfyUIPlaygroundPricing
discord logo
ComfyUI>Workflows>Flux Consistent Characters | Input Image

Flux Consistent Characters | Input Image

Workflow Name: RunComfy/ConsistentChar2-Flux
Workflow ID: 0000...1151
Updated 6/16/2025: ComfyUI version updated to v0.3.39 for improved stability and compatibility. The 'Flux Consistent Characters Workflow Series 2 (Input Image)' by Mickmumpitz is a helpful tool in ComfyUI for creating characters that look the same throughout your projects. It's perfect for things like AI movies or children's books where you need characters to have a consistent appearance. This tool makes it easier to keep characters looking uniform without needing numerous prompts or adjustments.

This "Flux Consistent Characters Workflow Series 2 (Input Image)" was created by Mickmumpitz on his YouTube channel. We highly recommend checking out his detailed tutorial to learn how to use this powerful Consistent Characters workflow effectively. While we've reproduced the Flux Consistent Characters workflow and set up the environment for your convenience, all credit goes to Mickmumpitz for his excellent work on developing this Flux-based Consistent Characters solution.

If you want to create Flux consistent characters with text input, please use the "Flux Consistent Characters Workflow Series 1 (Input Text)" by Mickmumpitz.

The Flux Consistent Characters (Input Image)

The Flux Consistent Characters (Input Image) Workflow is a powerful tool that enables you to generate AI characters that closely resemble a provided reference image. By utilizing the Flux-PuLID Model, this workflow ensures that the created characters maintain a high degree of visual consistency with your input images across various poses and angles. The Flux.1 dev model plays a crucial role in enhancing the stability and reliability of the generated characters. Whether you're working on animated films, illustrated storybooks, or any other visually-oriented project, this workflow streamlines the process of creating characters that accurately match your initial design, as depicted in the input image. With the Flux Consistent Characters (Input Image) Workflow, you can bring your character concepts to life with unparalleled fidelity and consistency.

How to Use the Flux Consistent Characters (Input Image) Workflow?

Here's a detailed guide on using the Flux Consistent Characters (Input Text) Please refer to this guide for more information.

The "Flux Consistent Characters (Input Image) Workflow" differs from the text-based one by using an image as input instead of text. In this image-based workflow, the author employs the Flux-PuLID model to maintain consistent facial identity across generated images.

1. Consistent Character Generation with Flux and Flux-PuLID

Flux Consistent Characters (Input Image)

Flux-PuLID is an innovative AI model that combines the capabilities of PuLID (Pure and Lightning ID Customization) with the powerful text-to-image generation of the FLUX model. It allows users to customize images, especially faces, to a specific identity while preserving the core functionality and image quality of the underlying FLUX model.

The key strength of Flux-PuLID lies in its ability to generate images with high identity similarity to the provided reference image. It achieves this by utilizing a contrastive alignment technique that minimizes disruption to the original FLUX model. At the same time, it employs a Lightning T2I branch that enables rapid generation of high-quality images from noise in a manageable number of steps. This Lightning T2I branch also allows the calculation of an accurate identity loss, ensuring the generated images faithfully capture the desired identity.

Another notable feature of Flux-PuLID is its editability. Users can modify attributes, styles, and backgrounds of the generated images using text prompts, providing extensive creative control. The model strives to maintain consistency in image elements like lighting, composition, and overall style before and after the identity customization process.

However, Flux-PuLID does have some limitations. While it generally performs well across a wide range of identities, the results may vary depending on the quality and characteristics of the input reference image. Very complex or abstract text prompts might also lead to less accurate identity preservation.

2. Upsacle + Face Fix

Flux Consistent Characters (Input Image)

3. Poses

Flux Consistent Characters (Input Image)

4. Emotions

Flux Consistent Characters (Input Image)

5. Add background

Flux Consistent Characters (Input Image)

License

View license files:

flux/model_licenses/LICENSE-FLUX1-dev

flux/model_licenses/LICENSE-FLUX1-schnell

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Want More ComfyUI Workflows?

Flux Consistent Characters | Input Text

Flux Consistent Characters | Input Text

Create consistent characters and ensure they look uniform by inputting text.

ACE-Step Music Generation | AI Audio Creation

Generate studio-quality music 15× faster with breakthrough diffusion technology.

Flux TTP Tile Upscale | Face Restoration

Repair distorted faces while upscaling images to 4K resolution.

Linear Mask Dilation | Stunning Animations

Transform your subjects and have them travel through different scenes seamlessly.

Epic CineFX | CogVideoX, ControlNet, and Live Portrait Workflow

Turn simple footage into epic film scenes with CogVideoX, ControlNet, and Live Portrait.

ComfyUI Img2Vid | Morphing Animation

Morphing animation with AnimateDiff LCM, IPAdapter, QRCode ControlNet, and Custom Mask modules.

ACE++ Face Swap | Image Editing

Swap faces in images with natural language instructions while preserving style and context.

Product Relighting | Magnific.AI Relight Alternative

Elevate your product photography effortlessly, a top alternative to Magnific.AI Relight.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Resources
  • Free ComfyUI Online
  • ComfyUI Guides
  • RunComfy API
  • ComfyUI Tutorials
  • ComfyUI Nodes
  • Learn More
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Playground, enabling artists to harness the latest AI tools to create incredible art.