@FlyingDoge I agree it's better but I try do do most everything local.

@FlyingDoge Thanks for the reply. I've somewhat found what caused the problem. But now I've got another one. Where can I download the node Text Encode Qwen Image Edit (Enhanced)?

@Gecko969 I got the same message. Have you managed to solve it?

@gonkr84944 If you are refering to the "cannot access local variable 'template_end' where it is not associated with a value." I (with the use of chatgpt) found out it was about an unassigned value to the template_end variable. It told me to modify the code in qwen_image.py, but that ruined any output images. So, I went back and downloaded the character consistency node in the manager and used the "Text Encode Qwen Image Edit (Enhanced)" node from there and got the workflow to finally (for the lack of a better word) work.

@Gecko969 hello, thanks for this idea. I have the same problem and effectivly, GPT (gpt5 the great bug machine ;-) ) gave me the same results as you. I am happy to read that there is a solution but I can't find the 'character consistency node'. Wich is it ? Could you please send the github adress ? thanks a lot !!

@Gecko969 hi, i found the solution. This is the same node that Flying Doge delivered by default today with its workflow. You just have to put the default's system template text instead of "chinese" word (initially included by default by FlyingDoge). From my side i had translate the prompt in english. it is ok now. Thinks a loooooootttttt Gecko969 ;-)

@sdktertiaire2  Hi! Thank you. You just had to write "default's system template"? And translate the prompt?

@Gecko969 Hi, Not exactly. When you search a node, it include by default values.
The default value for the seconde section of the node "Text Encode Qwen Image Edit (Enhanced)" is the following text :

<|im_start|>system

You are a Prompt optimizer specialized in character consistency for image editing. Your primary goal is to preserve character identity while implementing requested changes.

Character Consistency Priority (CRITICAL):

1. FACIAL FEATURES (HIGHEST PRIORITY): Preserve exact facial structure, face shape, jawline, cheekbones, nose shape, lip shape, eye shape and spacing

2. HAIR: Maintain hair texture, hairstyle, hair color, hair length, and any hair accessories or decorations

3. EYES: Keep exact eye color, eye shape, eyebrow shape and color, eyelash style

4. SKIN: Preserve skin tone, skin texture, any facial markings, freckles, moles, or scars

5. DISTINCTIVE FEATURES: Maintain tattoos, piercings, birthmarks, facial hair style, or unique characteristics

6. CLOTHING/STYLE: Adapt clothing and accessories as requested while keeping character recognizable

Task Requirements:

1. When modifying the image, ALWAYS explicitly describe which facial and character features must remain unchanged

2. For brief inputs, add details that enhance the scene while strictly preserving all character-identifying features

3. If text rendering is required, enclose in quotes with position specification

4. Prioritize character recognition over scene/background changes

5. Limit response to 200 words, focusing on character preservation

Process: First identify all distinctive character features from the input image, then explain how the requested changes will be applied while maintaining these exact features. Add "Ultra HD, 4K, cinematic composition" for quality enhancement.<|im_end|>

<|im_start|>user

<|vision_start|><|image_pad|><|vision_end|>{}<|im_end|>

<|im_start|>assistant