modèles/Action SDXL - V0.5

Action SDXL - V0.5

11/18/2025

4:24:55 PM

Mots-clés et tags associés

action camera angles,action sdxl,camera angle,dynamic poses,lora,lora model,pose,sdxl 1.0,outil,tools,v0.5,zdyna_pose,zovya,zpose,zstyle

Dramatic black and white cinematic shot of a massive King Kong rampaging through 1930s New York City streets amid destruction and smoke, viewed from a low angle.

A monstrous creature with large orange eyes and sharp teeth lunges forward in a wet and dirty sewer tunnel, captured from a low cinematic point of view with dramatic lighting.

A female rock climber with determined expression ascends a steep cliff in a vast rocky desert landscape, captured from a bird's eye third-person POV.

Prompts recommandés

zdyna_pose,posing in zdyna_pose,dutch angle,foreshortening,motion blur,from above,from below,blurred foreground

zdyna_pose, dutch angle, from below, foreground objects dust and volumetric lighting, bright cinematic lighting, orange and teal color grading

Prompts négatifs recommandés

sepia

Paramètres recommandés

samplers

DPM++ 2S a Karras

steps

cfg

Conseils

Use the trigger word 'zdyna_pose' in the positive prompt to activate the model.

Incorporate keywords such as 'dutch angle', 'foreshortening', 'motion blur', 'from above', 'from below', and 'blurred foreground' to enhance dynamic effects.

The model works at full strength and is not overtrained, so high impact prompts deliver good results.

Sponsors du créateur

Follow me to make sure you see new tools like this, or new styles, poses and Nobodys when I post them. More Clutter series coming too. Things move fast on this site, it's easy to miss.

Buy me a beer on Ko-Fi to support my work and request features.

Tired of boring images and can't be bothered to use controlnet? Use this LoRA and it will add dynamic poses, action camera angles and lots of energy and movement to your images.

Follow me to make sure you see new tools like this, or new styles, poses and Nobodys when I post them. More Clutter series coming too. Things move fast on this site, it's easy to miss.

How to use:
Works at full strength, not overtrained. Use the trigger word zdyna_pose in the positive prompt. Some other useful keywords are posing in zdyna_pose, dutch angle, foreshortening, motion blur, from above, from below, blurred foreground.

Preview Images:
Were generated using ComfyUI and/or InvokeAI. Special thanks to EDG for technical advice in training this concept.

Do you have requests? I've been putting in many more hours lately with this. That's my problem, not yours. But if you'd like to tip me, buy me a beer. Beer encourages me to ignore work and make AI models instead. Tip and make a request. I'll give it a shot if I can. Here at Ko-Fi