Skip to content
WorkflowListedExternal
Open source

Kontext character creator — v2.0-extras

Create images of a character in other positions for LoRa training

TaskMultiCapabilitiesImage to image · Text to imageFamilyFLUXEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Source
Civitai
Updated
Oct 2, 2026

Source description

Create images of a character in other positions for LoRa training

Some examples of prompts that I used to test.

Recreate the character from the first image in three anatomical views: front, side (profile), and back, matching the exact pose and perspective of the reference model on the second image. Maintain full consistency in the character's identity, including facial features, hair, clothes and accessories. Preserve the style, lighting, rich textures, and realistic anatomical proportions. Ensure that each new pose captures the same costume flow and detail placement from the original character design.

Reposition the fantasy warrior character into a new distinct dynamic pose while preserving all original details, including his face, hair, clothes and accessories.

Maintain the original style, lighting, and rich texture quality throughout all poses. Character anatomy, costume elements, and personality must remain consistent.

Walking Calmly:

Show the character walking forward at a relaxed pace, with a neutral or thoughtful expression. His hands can rest naturally at his sides casually. Clothes and hair flow subtly with the motion.

Standing with Arms Crossed:

Depict the character standing in place with his arms crossed over his chest, conveying patience or contemplation. Keep the body relaxed but firm, expressing wisdom or calm authority.

Looking Over Shoulder:

Show the character in a slight twist, glancing back over one shoulder as if reacting to a sound or presence behind him. This should be a subtle motion—no combat stance—just curiosity or awareness. Maintain natural posture and relaxed expression.

Sitting Pose:

Depict the character sitting on a stone throne or ancient bench, maintaining a powerful and composed expression. Clothes should flow naturally around the seated form.

Jumping Pose:

Show the character mid-air in an action-oriented leap, clothes and hair flowing dynamically to convey motion, and a focused, intense expression.

Running Pose:

Display the character in full stride, running with determination. The clothes trailing behind, and the body leaning slightly forward for momentum. Ensure proper motion blur or implied movement for realism.

Pointing:

Show the character with one hand extended forward, pointing to the camera.

Kneeling:

Depict the character in a solemn kneeling position and both hands resting on his lap. His expression should be calm or contemplative, suggesting honor, memory, or ritual. Maintain detailed costume flow and realistic weight distribution.

Defensive Stance:

Show the character in a guarded, battle-ready pose, feet planted wide, and body turned slightly sideways. His expression should be alert and prepared, with clothes and hair positioned naturally to reflect a tense, ready posture.

What you need

Model files
9.9 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

9

Node packs

11
  • CLIPTextEncode

    Possible

    Node pack · Unknown

  • EmptyLatentImage

    Possible

    Node pack · Unknown

  • FluxGuidance

    Not resolved

    Node pack · Unknown

  • FluxKontextImageScale

    Not resolved

    Node pack · Unknown

  • ImageStitch

    Possible

    Node pack · Unknown

  • KSampler

    Possible

    Node pack · Unknown

  • LoadImage

    Possible

    Node pack · Unknown

  • PreviewImage

    Possible

    Node pack · Unknown

  • PrimitiveInt

    Not resolved

    Node pack · Unknown

  • Node pack · Unknown

  • UNETLoader

    Possible

    Node pack · Unknown

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • Kontext character creator is for creating character images in new positions for LoRa training. Give it a character image, a pose or perspective reference image, and a text prompt; it can produce alternate views and poses.

Flow

  • Start with a character image and a pose or perspective reference, then describe the requested view or pose in your prompt.

    Suggestion · not verified

Inputs and outputs

  • Inputs are a character image, a pose or perspective reference image, and a text prompt.

  • Described outputs include front, side (profile), and back views, plus standing with arms crossed, looking over a shoulder, sitting, jumping, running, pointing, kneeling, and defensive stances.

Setup

  • The listed base model is Flux.1 Kontext.

Dependencies

  • Listed model files are: ae.safetensors, Flux/ae.safetensors, Flux/clip_l.safetensors, Flux/flux1Kontext_flux1KontextDev.safetensors, and Flux/t5xxl_fp16.safetensors.

  • Listed nodes include: LoadImage, ReferenceLatent, CLIPTextEncode, DualCLIPLoader, EmptyLatentImage, FluxGuidance, FluxKontextImageScale, and ImageStitch.

  • Other listed nodes are: KSampler, PreviewImage, PrimitiveInt, UNETLoader, VAEDecode, VAEEncode, and VAELoader.

Configuration

  • For a three-view set, ask for front, side (profile), and back in the prompt.

    Suggestion · not verified

  • To request consistent character details, include facial features, hair, clothes, accessories, style, lighting, textures, anatomy, and costume details in the prompt.

    Suggestion · not verified

Cautions

  • Before use, verify that the listed model files and nodes are available in your environment.

    Suggestion · not verified

  • No usage license is listed; verify the applicable terms before use.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimary
civitai.com/models/1722303

Verified Jul 19

Source excerpts

1 excerpt

Source context: 4859 downloads · Type Workflows · Base model Flux.1 Kontext