omniedgeio/deepfashionsdxl 🔢🖼️📝❓✓ → 🖼️

▶️ 1.3K runs 📅 Jun 2024 ⚙️ Cog 0.9.4
image-inpainting image-to-image nsfw text-to-image

About

Generate high resolution image

Example Output

Prompt:

"a young woman in a floral bikini stands on a beach, posing for a photo. she wears a necklace and seems to be enjoying her time at the beach. the sunset in the background adds a serene and picturesque atmosphere. the woman is the focal point of the scene, with the beach and sunset creating a peaceful and relaxing environment."

Output

Example output

Performance Metrics

16.56s Prediction Time
226.90s Total Time
All Input Parameters
{
  "hdr": 1,
  "width": 1024,
  "height": 1024,
  "prompt": "a young woman in a floral bikini stands on a beach, posing for a photo. she wears a necklace and seems to be enjoying her time at the beach. the sunset in the background adds a serene and picturesque atmosphere. the woman is the focal point of the scene, with the beach and sunset creating a peaceful and relaxing environment.",
  "refine": "base_image_refiner",
  "strength": 0.8,
  "scheduler": "DPMSolverSinglestepScheduler",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "refine_steps": 10,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "condition_scale": 1.1,
  "high_noise_frac": 0.8,
  "negative_prompt": "illustration, cropped face, cover face, cover visage, mutated hands, bad anatomy, bad hands, three hands, three legs, bad arms,missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate, not human, no head,low quality, worst quality, cgi, extra limbs, cleavage, pencil drawing, black and white, greyscale, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
  "prompt_strength": 0.8,
  "num_inference_steps": 28
}
Input Parameters
hdr Type: numberDefault: 0Range: 0 - 1
HDR improvement over the original image
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
img2img Type: boolean
Use img2img pipeline, it will use the image input both as the control image and the base image.
strength Type: numberDefault: 0.8Range: 0 - 1
When img2img is active, the denoising strength. 1 means total destruction of the input image.
scheduler Default: K_EULER
scheduler
controlnet Type: boolean
controlnet
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.
clothes_type Default: Dress
Format of the output images
refine_steps Type: integerDefault: 10
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
condition_scale Type: numberDefault: 1.1Range: 0 - 2
The bigger this number is, the more ControlNet interferes
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
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
replicate_weights_url Type: string
Replicate LoRA weights to use. Leave blank to use the default weights.
disable_safety_checker Type: booleanDefault: true
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 37898
Prompt: a young woman in a floral bikini stands on a beach, posing for a photo. she wears a necklace and seems to be enjoying her time at the beach. the sunset in the background adds a serene and picturesque atmosphere. the woman is the focal point of the scene, with the beach and sunset creating a peaceful and relaxing environment.
txt2img mode
The config attributes {'final_sigmas_type': 'zero', 'sigma_max': None, 'sigma_min': None, 'timestep_type': 'discrete'} were passed to DPMSolverSinglestepScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:03,  8.03it/s]
  7%|▋         | 2/28 [00:00<00:03,  8.46it/s]
 11%|█         | 3/28 [00:00<00:02,  8.63it/s]
 14%|█▍        | 4/28 [00:00<00:02,  8.73it/s]
 18%|█▊        | 5/28 [00:00<00:02,  8.77it/s]
 21%|██▏       | 6/28 [00:00<00:02,  8.79it/s]
 25%|██▌       | 7/28 [00:00<00:02,  8.82it/s]
 29%|██▊       | 8/28 [00:00<00:02,  8.81it/s]
 32%|███▏      | 9/28 [00:01<00:02,  8.81it/s]
 36%|███▌      | 10/28 [00:01<00:02,  8.80it/s]
 39%|███▉      | 11/28 [00:01<00:01,  8.80it/s]
 43%|████▎     | 12/28 [00:01<00:01,  8.80it/s]
 46%|████▋     | 13/28 [00:01<00:01,  8.80it/s]
 50%|█████     | 14/28 [00:01<00:01,  8.80it/s]
 54%|█████▎    | 15/28 [00:01<00:01,  8.80it/s]
 57%|█████▋    | 16/28 [00:01<00:01,  8.80it/s]
 61%|██████    | 17/28 [00:01<00:01,  8.81it/s]
 64%|██████▍   | 18/28 [00:02<00:01,  8.80it/s]
 68%|██████▊   | 19/28 [00:02<00:01,  8.80it/s]
 71%|███████▏  | 20/28 [00:02<00:00,  8.80it/s]
 75%|███████▌  | 21/28 [00:02<00:00,  8.80it/s]
 79%|███████▊  | 22/28 [00:02<00:00,  8.80it/s]
 82%|████████▏ | 23/28 [00:02<00:00,  8.80it/s]
 86%|████████▌ | 24/28 [00:02<00:00,  8.80it/s]
 89%|████████▉ | 25/28 [00:02<00:00,  8.80it/s]
 93%|█████████▎| 26/28 [00:02<00:00,  8.80it/s]
 96%|█████████▋| 27/28 [00:03<00:00,  8.80it/s]
100%|██████████| 28/28 [00:03<00:00,  8.80it/s]
100%|██████████| 28/28 [00:03<00:00,  8.78it/s]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:00,  7.44it/s]
 67%|██████▋   | 2/3 [00:00<00:00,  7.67it/s]
100%|██████████| 3/3 [00:00<00:00,  7.75it/s]
100%|██████████| 3/3 [00:00<00:00,  7.70it/s]
/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=None`.
warnings.warn(msg)
Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth" to /src/gfpgan/weights/detection_Resnet50_Final.pth
  0%|          | 0.00/104M [00:00<?, ?B/s]
 20%|██        | 21.3M/104M [00:00<00:00, 224MB/s]
 48%|████▊     | 50.3M/104M [00:00<00:00, 271MB/s]
 93%|█████████▎| 96.9M/104M [00:00<00:00, 370MB/s]
100%|██████████| 104M/104M [00:00<00:00, 346MB/s]
Downloading: "https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth" to /src/gfpgan/weights/parsing_parsenet.pth
  0%|          | 0.00/81.4M [00:00<?, ?B/s]
 26%|██▌       | 21.3M/81.4M [00:00<00:00, 223MB/s]
 71%|███████▏  | 58.1M/81.4M [00:00<00:00, 319MB/s]
100%|██████████| 81.4M/81.4M [00:00<00:00, 342MB/s]
Version Details
Version ID
c5a81f3e847a328821191ae8aee7f9d5693d2f59635df444ae8c1d2bc3cd93a5
Version Created
July 31, 2024
Run on Replicate →