falahgs/sdxl-lora_photorealistic_female 🖼️🔢📝❓✓ → 🖼️

▶️ 233 runs 📅 Jan 2024 ⚙️ Cog 0.8.2
image-inpainting image-to-image text-to-image

About

Example Output

Prompt:

"cinematic film still center of view camera , still photorealistic, ultra-realistic, glowing color hair, 40 year old man,blue detailed eyes, long blue theme, eyeshadow, mascara, plush lips, pink lipstick, smile, straight white teeth, realistic skin texture, skin pores, shiny skin, selfie, red dress, photo shoot, rain background, alluring, attractive, amazing photograph, masterpiece, best quality, . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy"

Output

Example outputExample output

Performance Metrics

17.44s Prediction Time
26.12s Total Time
All Input Parameters 
{
  "width": 768,
  "height": 768,
  "prompt": "cinematic film still  center of view camera , still photorealistic, ultra-realistic, glowing color hair,   40 year old man,blue detailed  eyes, long blue theme, eyeshadow, mascara, plush lips, pink lipstick, smile, straight white teeth, realistic skin texture, skin pores, shiny skin, selfie, red dress, photo shoot, rain  background, alluring, attractive, amazing photograph, masterpiece, best quality, . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope,  . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
  "refine": "no_refiner",
  "scheduler": "DDIM",
  "lora_scale": 0.6,
  "num_outputs": 2,
  "guidance_scale": 7,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, ugly, deformed, noisy, blurry, distorted, grainy, ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, cheerful, optimistic, anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured,breast, boobs,",
  "prompt_strength": 0.8,
  "num_inference_steps": 25
}
Input Parameters
mask Type: string
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer
Random seed. Leave blank to randomize the seed
image Type: string
Input image for img2img or inpaint mode
width Type: integerDefault: 1024
Width of output image
height Type: integerDefault: 1024
Height of output image
prompt Type: stringDefault: An astronaut riding a rainbow unicorn
Input prompt
refine Default: no_refiner
Which refine style to use
scheduler Default: K_EULER
scheduler
lora_scale Type: numberDefault: 0.6Range: 0 - 1
LoRA additive scale. Only applicable on trained models.
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
refine_steps Type: integer
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
guidance_scale Type: numberDefault: 7.5Range: 1 - 50
Scale for classifier-free guidance
apply_watermark Type: booleanDefault: true
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
high_noise_frac Type: numberDefault: 0.8Range: 0 - 1
For expert_ensemble_refiner, the fraction of noise to use
negative_prompt Type: stringDefault:
Input Negative Prompt
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
replicate_weights Type: string
Replicate LoRA weights to use. Leave blank to use the default weights.
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
Using seed: 33848
Ensuring enough disk space...
Free disk space: 1662440103936
Downloading weights: https://replicate.delivery/pbxt/93LIBsTR9O7wBVqmh0hpat6gQxRWqDGcs61ie1bqjMufkrKSA/trained_model.tar
2024-01-09T08:48:31Z | INFO  | [ Initiating ] dest=/src/weights-cache/97c969dae99117dd minimum_chunk_size=150M url=https://replicate.delivery/pbxt/93LIBsTR9O7wBVqmh0hpat6gQxRWqDGcs61ie1bqjMufkrKSA/trained_model.tar
2024-01-09T08:48:38Z | INFO  | [ Complete ] dest=/src/weights-cache/97c969dae99117dd size="186 MB" total_elapsed=6.531s url=https://replicate.delivery/pbxt/93LIBsTR9O7wBVqmh0hpat6gQxRWqDGcs61ie1bqjMufkrKSA/trained_model.tar
b''
Downloaded weights in 6.680342197418213 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: cinematic film still  center of view camera , still photorealistic, ultra-realistic, glowing color hair,   40 year old man,blue detailed  eyes, long blue theme, eyeshadow, mascara, plush lips, pink lipstick, smile, straight white teeth, realistic skin texture, skin pores, shiny skin, selfie, red dress, photo shoot, rain  background, alluring, attractive, amazing photograph, masterpiece, best quality, . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope,  . shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
txt2img mode
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['attractive, amazing photograph, masterpiece, best quality,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy', 'attractive, amazing photograph, masterpiece, best quality,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy']
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['attractive, amazing photograph, masterpiece, best quality,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy', 'attractive, amazing photograph, masterpiece, best quality,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope,. shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy']
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:00<00:07,  3.35it/s]
  8%|▊         | 2/25 [00:00<00:06,  3.34it/s]
 12%|█▏        | 3/25 [00:00<00:06,  3.33it/s]
 16%|█▌        | 4/25 [00:01<00:06,  3.32it/s]
 20%|██        | 5/25 [00:01<00:06,  3.32it/s]
 24%|██▍       | 6/25 [00:01<00:05,  3.32it/s]
 28%|██▊       | 7/25 [00:02<00:05,  3.31it/s]
 32%|███▏      | 8/25 [00:02<00:05,  3.31it/s]
 36%|███▌      | 9/25 [00:02<00:04,  3.32it/s]
 40%|████      | 10/25 [00:03<00:04,  3.31it/s]
 44%|████▍     | 11/25 [00:03<00:04,  3.31it/s]
 48%|████▊     | 12/25 [00:03<00:03,  3.31it/s]
 52%|█████▏    | 13/25 [00:03<00:03,  3.31it/s]
 56%|█████▌    | 14/25 [00:04<00:03,  3.31it/s]
 60%|██████    | 15/25 [00:04<00:03,  3.31it/s]
 64%|██████▍   | 16/25 [00:04<00:02,  3.31it/s]
 68%|██████▊   | 17/25 [00:05<00:02,  3.31it/s]
 72%|███████▏  | 18/25 [00:05<00:02,  3.31it/s]
 76%|███████▌  | 19/25 [00:05<00:01,  3.31it/s]
 80%|████████  | 20/25 [00:06<00:01,  3.31it/s]
 84%|████████▍ | 21/25 [00:06<00:01,  3.30it/s]
 88%|████████▊ | 22/25 [00:06<00:00,  3.31it/s]
 92%|█████████▏| 23/25 [00:06<00:00,  3.30it/s]
 96%|█████████▌| 24/25 [00:07<00:00,  3.30it/s]
100%|██████████| 25/25 [00:07<00:00,  3.30it/s]
100%|██████████| 25/25 [00:07<00:00,  3.31it/s]
Version Details
Version ID
187ff51fc19e13d88a479284e44bf2eee4244509f751db2fbd05aff8d50bf8e7
Version Created
January 9, 2024
Run on Replicate →