z_image_turbo / README.md
ReCodePlus's picture
initial commit
cc3a078 verified
metadata
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - output:
      url: images/c1.jpg
    text: >-
      Smnth_v1, extreme close-up portrait of a woman with dark hair and brown
      eyes, soft pink blush on cheeks, natural skin texture, long eyelashes,
      looking directly at the camera, neutral expression, soft natural lighting,
      high detail, 8k resolution.
    parameters:
      negative_prompt: >-
        (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render,
        sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of
        frame, worst quality, low quality, jpeg artifacts, ugly, duplicate,
        morbid, mutilated, extra fingers, mutated hands, poorly drawn hands,
        poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy,
        bad proportions, extra limbs, cloned face, disfigured, gross
        proportions, malformed limbs, missing arms, missing legs, extra arms,
        extra legs, fused fingers, too many fingers, long neck.
  - output:
      url: images/c6.jpg
    text: >-
      Smnth_v1, full body shot, standing against a plain white wall, wearing a
      beige ribbed tank top and black jeans, dark hair, natural lighting,
      minimalistic background, high detail, realistic skin, cinematic lighting.
    parameters:
      negative_prompt: >-
        (worst quality, low quality:1.4), text, watermark, logo, signature,
        blurry, lowres, extra limbs, bad anatomy, disfigured, mutated, cartoon,
        3d, illustration, drawing.
  - output:
      url: images/c18.jpg
    text: >-
      Smnth_v1, full body shot, sitting on a wooden floor near a large window,
      wearing a black scoop neck t-shirt and black denim shorts, natural indoor
      lighting, soft shadows, dark hair, looking at camera, cinematic
      composition, highly detailed.
    parameters:
      negative_prompt: >-
        (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong
        anatomy, extra limb, missing limb, floating limbs, (mutated hands and
        fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting,
        blurry, amputation.
base_model: Tongyi-MAI/Z-Image-Turbo
instance_prompt: Smnth_v1
license: openrail

Sam

Prompt
Smnth_v1, extreme close-up portrait of a woman with dark hair and brown eyes, soft pink blush on cheeks, natural skin texture, long eyelashes, looking directly at the camera, neutral expression, soft natural lighting, high detail, 8k resolution.
Negative Prompt
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck.
Prompt
Smnth_v1, full body shot, standing against a plain white wall, wearing a beige ribbed tank top and black jeans, dark hair, natural lighting, minimalistic background, high detail, realistic skin, cinematic lighting.
Negative Prompt
(worst quality, low quality:1.4), text, watermark, logo, signature, blurry, lowres, extra limbs, bad anatomy, disfigured, mutated, cartoon, 3d, illustration, drawing.
Prompt
Smnth_v1, full body shot, sitting on a wooden floor near a large window, wearing a black scoop neck t-shirt and black denim shorts, natural indoor lighting, soft shadows, dark hair, looking at camera, cinematic composition, highly detailed.
Negative Prompt
(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation.

Model description

This is a LoRA trained on the Z-Image-Turbo base model. It is designed to capture the likeness of Sam.

Trigger word: Smnth_v1

Best used with: Z-Image-Turbo base model.

Training details: Trained for approximately 3000 steps with a learning rate of 0.00005.

Trigger words

You should use Smnth_v1 to trigger the image generation.

Download model

Download them in the Files & versions tab.