zedge/instantid 🔢📝✓🖼️❓ → ❓

▶️ 6.5M runs 📅 Nov 2024 ⚙️ Cog 0.15.2
image-consistent-character-generation image-to-image

About

Example Output

Prompt:

"{{image_caption}}, Post-apocalyptic wasteland, portrait of a survivor, ruined cityscape, overgrown vegetation, abandoned buildings, muted colors, atmospheric haze, survival gear, tattered clothing, gritty realism, cinematic lighting, dramatic shadows, emotional depth, environmental storytelling"

Output

Performance Metrics

5.07s Prediction Time
5.07s Total Time
All Input Parameters
{
  "prompt": "{{image_caption}}, Post-apocalyptic wasteland, portrait of a survivor, ruined cityscape, overgrown vegetation, abandoned buildings, muted colors, atmospheric haze, survival gear, tattered clothing, gritty realism, cinematic lighting, dramatic shadows, emotional depth, environmental storytelling",
  "verbose": false,
  "scheduler": "EulerDiscreteScheduler",
  "enable_lcm": false,
  "force_clip": false,
  "input_image": "https://replicate.delivery/pbxt/MVyVpNevu56yR1lMay1y9Ap9We67j3V4WZujCfByv3V2nt5t/cat.webp",
  "num_outputs": 1,
  "debug_images": false,
  "sdxl_weights": "RealVisXL_V5.0",
  "guidance_scale": 5,
  "megapixel_count": 1,
  "negative_prompt": "nsfw, nude, blurry, out of focus, low quality, disfigured, deformed, watermark, text, logo, signature, mutated, jpeg artifacts",
  "ip_adapter_scale": 0.8,
  "lcm_guidance_scale": 1.5,
  "num_inference_steps": 30,
  "disable_nsfw_checker": false,
  "enhance_nonface_region": true,
  "img2img_canny_strength": 0.45,
  "img2img_depth_strength": 0.85,
  "instantid_pose_strength": 0,
  "lcm_num_inference_steps": 5,
  "instantid_canny_strength": 0,
  "instantid_depth_strength": 0.3,
  "identitynet_strength_ratio": 0.8
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
prompt Type: stringDefault: vector art, vibrant neon colors, retro 80s Miami aesthetic, bold outlines, flat shading, urban cityscape background, palm trees, sunset sky, comic book style, high contrast, saturated colors
Input prompt
verbose Type: booleanDefault: false
Print detailed timing information
input_zip Type: string
ZIP file containing input images.
scheduler Default: EulerDiscreteScheduler
Scheduler
enable_lcm Type: booleanDefault: false
Enable Fast Inference with LCM (Latent Consistency Models) - speeds up inference steps, trade-off is the quality of the generated image. Performs better with close-up portrait face images
force_clip Type: booleanDefault: false
(DEPRECATED) Force using CLIP captioning regardless of face detection
warm_delay Type: integer
Parameter for warming the model. If set, returns empty dict after specified seconds
input_image Type: string
Input face image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output
debug_images Type: booleanDefault: false
(PARAMETER ONLY RELEVANT IN DEVELOPMENT) Save debug images
sdxl_weights Default: RealVisXL_V5.0
Pick which base weights you want to use
guidance_scale Type: numberDefault: 7.5Range: 1 - 50
Scale for classifier-free guidance
megapixel_count Type: numberDefault: 1
Megapixel count for image downscaling. 1024x1024 resolution is equal to 1 megapixel
negative_prompt Type: stringDefault: nsfw, nude, watermark, text, logo, signature, jpeg artifacts, blurry, out of focus, low quality, disfigured, deformed, mutated, ugly
Input Negative Prompt
ip_adapter_scale Type: numberDefault: 0.8Range: 0 - 1.5
ONLY FOR INSTANTID: Scale for image adapter strength (for detail)
lcm_guidance_scale Type: numberDefault: 1.5Range: 1 - 20
Only used when `enable_lcm` is set to True, Scale for classifier-free guidance when using LCM
num_inference_steps Type: integerDefault: 30Range: 1 - 500
Number of denoising steps
disable_nsfw_checker Type: booleanDefault: false
Disable safety checker for generated images.
enhance_nonface_region Type: booleanDefault: true
ONLY FOR INSTANTID: Enhance non-face region
img2img_canny_strength Type: numberDefault: 0Range: 0 - 1
ONLY FOR 0 FACES: Canny ControlNet strength, effective only if > 0
img2img_depth_strength Type: numberDefault: 0.7Range: 0 - 1
ONLY FOR 0 FACES: Depth ControlNet strength, effective only if > 0
instantid_pose_strength Type: numberDefault: 0Range: 0 - 1
ONLY FOR INSTANTID: Openpose ControlNet strength, effective only if > 0
lcm_num_inference_steps Type: integerDefault: 5Range: 1 - 10
Only used when `enable_lcm` is set to True, Number of denoising steps when using LCM
instantid_canny_strength Type: numberDefault: 0.3Range: 0 - 1
ONLY FOR INSTANTID: Canny ControlNet strength, effective only if > 0
instantid_depth_strength Type: numberDefault: 0.8Range: 0 - 1
ONLY FOR INSTANTID: Depth ControlNet strength, effective only if > 0
identitynet_strength_ratio Type: numberDefault: 0.8Range: 0 - 1.5
ONLY FOR INSTANTID: Scale for IdentityNet strength (for fidelity)
Output Schema

Output

Type: object

Example Execution Logs
Setting `pad_token_id` to `eos_token_id`:None for open-end generation.
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:02,  9.69it/s]
  7%|▋         | 2/30 [00:00<00:02,  9.87it/s]
 13%|█▎        | 4/30 [00:00<00:02, 10.05it/s]
 20%|██        | 6/30 [00:00<00:02, 10.15it/s]
 27%|██▋       | 8/30 [00:00<00:02, 10.14it/s]
 33%|███▎      | 10/30 [00:00<00:01, 10.12it/s]
 40%|████      | 12/30 [00:01<00:01, 10.16it/s]
 47%|████▋     | 14/30 [00:01<00:01, 10.16it/s]
 53%|█████▎    | 16/30 [00:01<00:01, 10.12it/s]
 60%|██████    | 18/30 [00:01<00:01, 10.10it/s]
 67%|██████▋   | 20/30 [00:01<00:00, 10.13it/s]
 73%|███████▎  | 22/30 [00:02<00:00, 10.18it/s]
 80%|████████  | 24/30 [00:02<00:00, 10.24it/s]
 87%|████████▋ | 26/30 [00:02<00:00, 10.27it/s]
 93%|█████████▎| 28/30 [00:02<00:00, 10.22it/s]
100%|██████████| 30/30 [00:02<00:00, 10.25it/s]
100%|██████████| 30/30 [00:02<00:00, 10.17it/s]
Version Details
Version ID
ba2d5293be8794a05841a6f6eed81e810340142c3c25fab4838ff2b5d9574420
Version Created
June 19, 2025
Run on Replicate →