brunnolou/ginetta-stock 🖼️🔢📝❓✓ → 🖼️

▶️ 45 runs 📅 Aug 2023 ⚙️ Cog 0.8.2
image-inpainting image-to-image text-to-image

About

Ginetta.net office photos fine-tuned on SDXL

Example Output

Prompt:

"cinematic photo of a TOK monkey smiling wearing clothes standing at the TOK office having a casual conversation. 35mm photograph, macbook, film, bokeh, professional, 4k, highly detailed, plant background, New York architecture style."

Output

Example output

Performance Metrics

18.41s Prediction Time
23.05s Total Time
All Input Parameters 
{
  "width": 1024,
  "height": 1024,
  "prompt": "cinematic photo of a TOK monkey smiling wearing clothes standing at the TOK office having a casual conversation. 35mm photograph,  macbook, film, bokeh, professional, 4k, highly detailed, plant background, New York architecture style.",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
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: 26522
Ensuring enough disk space...
Free disk space: 1787674157056
Downloading weights: https://pbxt.replicate.delivery/t6GspIq8Rh6zKZH0UbJQBHW8120befAfDarAK0TsGZNfCJeLC/trained_model.tar
b'Downloaded 186 MB bytes in 0.523s (356 MB/s)\nExtracted 186 MB in 0.066s (2.8 GB/s)\n'
Downloaded weights in 0.8086977005004883 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: cinematic photo of a <s0><s1> monkey smiling wearing clothes standing at the <s0><s1> office having a casual conversation. 35mm photograph,  macbook, film, bokeh, professional, 4k, highly detailed, plant background, New York architecture style.
txt2img mode
  0%|          | 0/50 [00:00<?, ?it/s]/usr/local/lib/python3.9/site-packages/torch/nn/modules/conv.py:459: UserWarning: Applied workaround for CuDNN issue, install nvrtc.so (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:80.)
return F.conv2d(input, weight, bias, self.stride,
  2%|▏         | 1/50 [00:00<00:44,  1.11it/s]
  4%|▍         | 2/50 [00:01<00:25,  1.89it/s]
  6%|▌         | 3/50 [00:01<00:19,  2.43it/s]
  8%|▊         | 4/50 [00:01<00:16,  2.81it/s]
 10%|█         | 5/50 [00:01<00:14,  3.08it/s]
 12%|█▏        | 6/50 [00:02<00:13,  3.27it/s]
 14%|█▍        | 7/50 [00:02<00:12,  3.39it/s]
 16%|█▌        | 8/50 [00:02<00:12,  3.48it/s]
 18%|█▊        | 9/50 [00:03<00:11,  3.54it/s]
 20%|██        | 10/50 [00:03<00:11,  3.59it/s]
 22%|██▏       | 11/50 [00:03<00:10,  3.62it/s]
 24%|██▍       | 12/50 [00:03<00:10,  3.64it/s]
 26%|██▌       | 13/50 [00:04<00:10,  3.65it/s]
 28%|██▊       | 14/50 [00:04<00:09,  3.66it/s]
 30%|███       | 15/50 [00:04<00:09,  3.67it/s]
 32%|███▏      | 16/50 [00:04<00:09,  3.67it/s]
 34%|███▍      | 17/50 [00:05<00:08,  3.68it/s]
 36%|███▌      | 18/50 [00:05<00:08,  3.67it/s]
 38%|███▊      | 19/50 [00:05<00:08,  3.68it/s]
 40%|████      | 20/50 [00:06<00:08,  3.68it/s]
 42%|████▏     | 21/50 [00:06<00:07,  3.68it/s]
 44%|████▍     | 22/50 [00:06<00:07,  3.68it/s]
 46%|████▌     | 23/50 [00:06<00:07,  3.67it/s]
 48%|████▊     | 24/50 [00:07<00:07,  3.67it/s]
 50%|█████     | 25/50 [00:07<00:06,  3.67it/s]
 52%|█████▏    | 26/50 [00:07<00:06,  3.67it/s]
 54%|█████▍    | 27/50 [00:07<00:06,  3.67it/s]
 56%|█████▌    | 28/50 [00:08<00:05,  3.67it/s]
 58%|█████▊    | 29/50 [00:08<00:05,  3.67it/s]
 60%|██████    | 30/50 [00:08<00:05,  3.68it/s]
 62%|██████▏   | 31/50 [00:09<00:05,  3.67it/s]
 64%|██████▍   | 32/50 [00:09<00:04,  3.67it/s]
 66%|██████▌   | 33/50 [00:09<00:04,  3.67it/s]
 68%|██████▊   | 34/50 [00:09<00:04,  3.67it/s]
 70%|███████   | 35/50 [00:10<00:04,  3.67it/s]
 72%|███████▏  | 36/50 [00:10<00:03,  3.67it/s]
 74%|███████▍  | 37/50 [00:10<00:03,  3.67it/s]
 76%|███████▌  | 38/50 [00:10<00:03,  3.67it/s]
 78%|███████▊  | 39/50 [00:11<00:03,  3.66it/s]
 80%|████████  | 40/50 [00:11<00:02,  3.66it/s]
 82%|████████▏ | 41/50 [00:11<00:02,  3.66it/s]
 84%|████████▍ | 42/50 [00:12<00:02,  3.66it/s]
 86%|████████▌ | 43/50 [00:12<00:01,  3.66it/s]
 88%|████████▊ | 44/50 [00:12<00:01,  3.66it/s]
 90%|█████████ | 45/50 [00:12<00:01,  3.66it/s]
 92%|█████████▏| 46/50 [00:13<00:01,  3.66it/s]
 94%|█████████▍| 47/50 [00:13<00:00,  3.66it/s]
 96%|█████████▌| 48/50 [00:13<00:00,  3.66it/s]
 98%|█████████▊| 49/50 [00:13<00:00,  3.66it/s]
100%|██████████| 50/50 [00:14<00:00,  3.66it/s]
100%|██████████| 50/50 [00:14<00:00,  3.51it/s]
Version Details
Version ID
9206b7d17a9c1de37f51ee93848956e54efa362ec79226da61f2f5a9c97d6e00
Version Created
August 31, 2023
Run on Replicate →