jagilley/stable-diffusion-depth2img 🔢📝❓🖼️ → 🖼️

▶️ 59.6K runs 📅 Jan 2023 ⚙️ Cog 0.6.1 🔗 GitHub ⚖️ License
depth-guided image-editing image-to-image

About

Create variations of an image while preserving shape and depth

Example Output

Prompt:

"wanderer above a cyberpunk city, 4k digital art rendering by caspar david friedrich"

Output

Example output

Performance Metrics

11.80s Prediction Time
21.58s Total Time
All Input Parameters 
{
  "seed": -1,
  "prompt": "wanderer above a cyberpunk city, 4k digital art rendering by caspar david friedrich",
  "scheduler": "DPMSolverMultistep",
  "input_image": "https://replicate.delivery/pbxt/ICo443xcFQGIK4lawWN3ytMNDZsmZS6fZfjGYwFP6Dc5Vfnq/wanderer.jpeg",
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: Wanderer above the sea of fog, digital art
The prompt to guide the image generation.
scheduler Default: DPMSolverMultistep
Choose a scheduler
depth_image Type: string
Depth image (optional). Specifies the depth of each pixel in the input image.
input_image (required) Type: string
Input image to be used as the starting point
num_outputs Type: integerDefault: 1Range: 1 - 8
Number of images to generate
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
negative_prompt Type: string
Keywords to exclude from the resulting image
prompt_strength Type: numberDefault: 0.8
Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image.
num_inference_steps Type: integerDefault: 50Range: 1 - 500
The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
Output Schema

Output

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

Example Execution Logs 
Using seed: -1
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:04<03:14,  4.99s/it]
  8%|▊         | 3/40 [00:05<00:49,  1.35s/it]
 12%|█▎        | 5/40 [00:05<00:24,  1.46it/s]
 18%|█▊        | 7/40 [00:05<00:13,  2.37it/s]
 22%|██▎       | 9/40 [00:05<00:08,  3.48it/s]
 28%|██▊       | 11/40 [00:05<00:06,  4.78it/s]
 32%|███▎      | 13/40 [00:05<00:04,  6.23it/s]
 38%|███▊      | 15/40 [00:05<00:03,  7.75it/s]
 42%|████▎     | 17/40 [00:06<00:02,  9.23it/s]
 48%|████▊     | 19/40 [00:06<00:01, 10.56it/s]
 52%|█████▎    | 21/40 [00:06<00:01, 11.78it/s]
 57%|█████▊    | 23/40 [00:06<00:01, 12.76it/s]
 62%|██████▎   | 25/40 [00:06<00:01, 13.49it/s]
 68%|██████▊   | 27/40 [00:06<00:00, 14.10it/s]
 72%|███████▎  | 29/40 [00:06<00:00, 14.60it/s]
 78%|███████▊  | 31/40 [00:06<00:00, 14.96it/s]
 82%|████████▎ | 33/40 [00:07<00:00, 15.19it/s]
 88%|████████▊ | 35/40 [00:07<00:00, 15.31it/s]
 92%|█████████▎| 37/40 [00:07<00:00, 15.46it/s]
 98%|█████████▊| 39/40 [00:07<00:00, 15.50it/s]
100%|██████████| 40/40 [00:07<00:00,  5.35it/s]
Version Details
Version ID
68f699d395bc7c17008283a7cef6d92edc832d8dc59eb41a6cafec7fc70b85bc
Version Created
January 26, 2023
Run on Replicate →