pilou57/piloupixar 🖼️🔢📝❓✓ → 🖼️

▶️ 3.2K runs 📅 May 2024 ⚙️ Cog 0.8.6
image-inpainting image-to-image pixar-style text-to-image

About

modèle pour faire des images de femme cohérentes

Example Output

Prompt:

"TOK, a girl with brown hairs and green eyes, proportional human body and face, jumping off a cliff, diving, in a bikini, people at the top of the cliff are watching, highly detailed, hyper textured, 3D render, vivid and vibrant colors, modern pixar animation style"

Output

Example output

Performance Metrics

27.23s Prediction Time
33.17s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "TOK, a girl with brown hairs and green eyes, proportional human body and face, jumping off a cliff, diving, in a bikini, people at the top of the cliff are watching, highly detailed, hyper textured, 3D render, vivid and vibrant colors, modern pixar animation style",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 9,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "sketch, flat, 2D, hand drawn",
  "prompt_strength": 1,
  "num_inference_steps": 40
}
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: 26794
Ensuring enough disk space...
Free disk space: 2046162583552
Downloading weights: https://replicate.delivery/pbxt/TSUhvKh0f53AaSoFcwKsRMYTgM6ODznRz6DtgtMaynPfx60SA/trained_model.tar
2024-05-16T14:21:58Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/7bb3b7093b96bc1f url=https://replicate.delivery/pbxt/TSUhvKh0f53AaSoFcwKsRMYTgM6ODznRz6DtgtMaynPfx60SA/trained_model.tar
2024-05-16T14:22:11Z | INFO  | [ Complete ] dest=/src/weights-cache/7bb3b7093b96bc1f size="186 MB" total_elapsed=13.060s url=https://replicate.delivery/pbxt/TSUhvKh0f53AaSoFcwKsRMYTgM6ODznRz6DtgtMaynPfx60SA/trained_model.tar
b''
Downloaded weights in 13.242272138595581 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: <s0><s1>, a girl with brown hairs and green eyes, proportional human body and face, jumping off a cliff, diving, in a bikini, people at the top of the cliff are watching, highly detailed, hyper textured, 3D render, vivid and vibrant colors, modern pixar animation style
txt2img mode
  0%|          | 0/32 [00:00<?, ?it/s]
  3%|▎         | 1/32 [00:00<00:08,  3.62it/s]
  6%|▋         | 2/32 [00:00<00:08,  3.61it/s]
  9%|▉         | 3/32 [00:00<00:08,  3.61it/s]
 12%|█▎        | 4/32 [00:01<00:07,  3.61it/s]
 16%|█▌        | 5/32 [00:01<00:07,  3.60it/s]
 19%|█▉        | 6/32 [00:01<00:07,  3.60it/s]
 22%|██▏       | 7/32 [00:01<00:06,  3.60it/s]
 25%|██▌       | 8/32 [00:02<00:06,  3.59it/s]
 28%|██▊       | 9/32 [00:02<00:06,  3.59it/s]
 31%|███▏      | 10/32 [00:02<00:06,  3.59it/s]
 34%|███▍      | 11/32 [00:03<00:05,  3.59it/s]
 38%|███▊      | 12/32 [00:03<00:05,  3.59it/s]
 41%|████      | 13/32 [00:03<00:05,  3.60it/s]
 44%|████▍     | 14/32 [00:03<00:05,  3.59it/s]
 47%|████▋     | 15/32 [00:04<00:04,  3.59it/s]
 50%|█████     | 16/32 [00:04<00:04,  3.59it/s]
 53%|█████▎    | 17/32 [00:04<00:04,  3.59it/s]
 56%|█████▋    | 18/32 [00:05<00:03,  3.59it/s]
 59%|█████▉    | 19/32 [00:05<00:03,  3.59it/s]
 62%|██████▎   | 20/32 [00:05<00:03,  3.59it/s]
 66%|██████▌   | 21/32 [00:05<00:03,  3.59it/s]
 69%|██████▉   | 22/32 [00:06<00:02,  3.58it/s]
 72%|███████▏  | 23/32 [00:06<00:02,  3.58it/s]
 75%|███████▌  | 24/32 [00:06<00:02,  3.59it/s]
 78%|███████▊  | 25/32 [00:06<00:01,  3.59it/s]
 81%|████████▏ | 26/32 [00:07<00:01,  3.58it/s]
 84%|████████▍ | 27/32 [00:07<00:01,  3.58it/s]
 88%|████████▊ | 28/32 [00:07<00:01,  3.58it/s]
 91%|█████████ | 29/32 [00:08<00:00,  3.58it/s]
 94%|█████████▍| 30/32 [00:08<00:00,  3.58it/s]
 97%|█████████▋| 31/32 [00:08<00:00,  3.59it/s]
100%|██████████| 32/32 [00:08<00:00,  3.59it/s]
100%|██████████| 32/32 [00:08<00:00,  3.59it/s]
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:01,  3.97it/s]
 25%|██▌       | 2/8 [00:00<00:01,  4.08it/s]
 38%|███▊      | 3/8 [00:00<00:01,  4.11it/s]
 50%|█████     | 4/8 [00:00<00:00,  4.11it/s]
 62%|██████▎   | 5/8 [00:01<00:00,  4.13it/s]
 75%|███████▌  | 6/8 [00:01<00:00,  4.13it/s]
 88%|████████▊ | 7/8 [00:01<00:00,  4.13it/s]
100%|██████████| 8/8 [00:01<00:00,  4.13it/s]
100%|██████████| 8/8 [00:01<00:00,  4.12it/s]
Version Details
Version ID
b9072915f1db2ae1e47cb569fe48a67ed9c5441aea8cdc7b237ef9cb43ef82fd
Version Created
May 16, 2024
Run on Replicate →