wolverinn / realistic-background

replace background with Stable Diffusion and ControlNet

  • Public
  • 134.2K runs
  • L40S
  • GitHub
  • License

Input

image
*file

Image to replace background

string
Shift + Return to add a new line

prompt en

Default: "RAW photo, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"

string
Shift + Return to add a new line

negative prompt

Default: "(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"

string

sampler name

Default: "DPM++ 2M SDE"

string

scheduler

Default: "Karras"

integer

steps

Default: 20

integer

generate count

Default: 1

integer

cfg scale

Default: 7

number

denoising strength

Default: 0.75

integer

max width

Default: 1024

integer

max height

Default: 1024

integer

only masked padding,pixels

Default: 4

integer

seed

Default: -1

Output

images

outputoutput

payload

{ "info": "{\"prompt\": \"RAW photo, car, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, neon city street\", \"all_prompts\": [\"RAW photo, car, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, neon city street\", \"RAW photo, car, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, neon city street\"], \"negative_prompt\": \"(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation\", \"all_negative_prompts\": [\"(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation\", \"(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation\"], \"seed\": 3447393137, \"all_seeds\": [3447393137, 3447393138], \"subseed\": 1674732274, \"all_subseeds\": [1674732274, 1674732275], \"subseed_strength\": 0, \"width\": 800, \"height\": 800, \"sampler_name\": \"DPM++ 2M SDE\", \"cfg_scale\": 7.0, \"steps\": 25, \"batch_size\": 2, \"restore_faces\": false, \"face_restoration_model\": null, \"sd_model_name\": \"realisticVisionV51_v51VAE\", \"sd_model_hash\": \"15012c538f\", \"sd_vae_name\": null, \"sd_vae_hash\": null, \"seed_resize_from_w\": -1, \"seed_resize_from_h\": -1, \"denoising_strength\": 0.75, \"extra_generation_params\": {\"Denoising strength\": 0.75, \"Mask mode\": \"Inpaint not masked\", \"Mask blur\": 2, \"Inpaint area\": \"Only masked\", \"Masked area padding\": 4, \"Masked content\": \"latent noise\", \"Schedule type\": \"Karras\"}, \"index_of_first_image\": 0, \"infotexts\": [\"RAW photo, car, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, neon city street\\nNegative prompt: (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation\\nSteps: 25, Sampler: DPM++ 2M SDE, Schedule type: Karras, CFG scale: 7.0, Seed: 3447393137, Size: 800x800, Model hash: 15012c538f, Model: realisticVisionV51_v51VAE, Denoising strength: 0.75, Mask mode: Inpaint not masked, Mask blur: 2, Inpaint area: Only masked, Masked area padding: 4, Masked content: latent noise, Version: 1.10.1\", \"RAW photo, car, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, neon city street\\nNegative prompt: (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation\\nSteps: 25, Sampler: DPM++ 2M SDE, Schedule type: Karras, CFG scale: 7.0, Seed: 3447393138, Size: 800x800, Model hash: 15012c538f, Model: realisticVisionV51_v51VAE, Denoising strength: 0.75, Mask mode: Inpaint not masked, Mask blur: 2, Inpaint area: Only masked, Masked area padding: 4, Masked content: latent noise, Version: 1.10.1\"], \"styles\": [], \"job_timestamp\": \"20240818144831\", \"clip_skip\": 1, \"is_using_inpainting_conditioning\": false, \"version\": \"1.10.1\"}" }
Generated in

This example was created by a different version, wolverinn/realistic-background:0b84aad9.

Run time and cost

This model costs approximately $0.025 to run on Replicate, or 40 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 26 seconds. The predict time for this model varies significantly based on the inputs.