usamaehsan/instant-id-x-juggernaut 🖼️🔢📝✓❓ → 🖼️

▶️ 94.5K runs 📅 Feb 2024 ⚙️ Cog 0.9.4

image-consistent-character-generation image-to-image

About

Example Output

Prompt:

"This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait"

Output

Performance Metrics

18.87s Prediction Time

194.45s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/KKhSlVNlQj10hguaYY8wbGgdaxvVBMQmm9Lw6a1PXiRrGCwj/53894527.jpg",
  "width": 1051,
  "height": 1040,
  "prompt": "This is Eric Draven The Crow Movie 1994 version, Brandon Lee, realistic, 8k, the crow bird, portrait",
  "max_side": 1280,
  "min_side": 1024,
  "scheduler": "UniPCMultistep",
  "resize_image": true,
  "guidance_scale": 3.5,
  "negative_prompt": "",
  "ip_adapter_scale": 1,
  "enhance_face_region": true,
  "num_inference_steps": 10,
  "micro_detail_lora_weight": 0,
  "controlnet_conditioning_scale": 0.6
}

Input Parameters

image Type: string: Input image
width Type: integerDefault: 640Range: 0 - 2048: Width for face detection
height Type: integerDefault: 640Range: 0 - 2048: Height for face detection
image2 Type: string: face image2
prompt Type: stringDefault: analog film photo of a man. faded film, desaturated, 35mm photo, grainy, vignette, vintage, Kodachrome, Lomography, stained, highly detailed, found footage, masterpiece, best quality: Input prompt
get_age Type: booleanDefault: true
max_side Type: integerDefault: 1280Range: 0 - 2048: min resolution // if resize image is on
min_side Type: integerDefault: 1024Range: 0 - 2048: min resolution // if resize image is on
scheduler Default: UniPCMultistep: Choose a scheduler.
pose_image Type: string: pose image
use_gfpgan Type: booleanDefault: true
resize_image Type: booleanDefault: true
guidance_scale Type: numberDefault: 5Range: 1 - 50: Scale for classifier-free guidance
negative_prompt Type: stringDefault:: Input Negative Prompt
ip_adapter_scale Type: numberDefault: 0.8Range: 0 - 5: Scale for IP adapter
enhance_face_region Type: booleanDefault: true
num_inference_steps Type: integerDefault: 30Range: 1 - 500: Number of denoising steps
use_controlnet_pose Type: booleanDefault: true
lightning_lora_weight Type: numberDefault: 0: disabled on 0 --> i thinkkk
micro_detail_lora_weight Type: numberDefault: 0: disabled on 0
controlnet_conditioning_scale Type: numberDefault: 0.8Range: 0 - 5: Scale for ControlNet conditioning
pose_controlnet_conditioning_scale Type: numberDefault: 0.8Range: 0 - 5: Scale for ControlNet conditioning

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

[!] Resizing output to 1051x1040
set det-size: (1051, 1040)
warning: det_size is already set in detection model, ignore
Time taken to resize image-- : -0.03 seconds
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/insightface/utils/transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions.
To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`.
P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4
Time taken to get face info-- : -6.44 seconds
Time taken to draw kps-- : -0.14 seconds
Time taken to enhance face region-- : -0.01 seconds
  0%|          | 0/10 [00:00<?, ?it/s]
 10%|█         | 1/10 [00:02<00:25,  2.80s/it]
 20%|██        | 2/10 [00:03<00:12,  1.55s/it]
 30%|███       | 3/10 [00:04<00:08,  1.16s/it]
 40%|████      | 4/10 [00:04<00:05,  1.04it/s]
 50%|█████     | 5/10 [00:05<00:04,  1.16it/s]
 60%|██████    | 6/10 [00:06<00:03,  1.26it/s]
 70%|███████   | 7/10 [00:06<00:02,  1.32it/s]
 80%|████████  | 8/10 [00:07<00:01,  1.37it/s]
 90%|█████████ | 9/10 [00:08<00:00,  1.40it/s]
100%|██████████| 10/10 [00:08<00:00,  1.43it/s]
100%|██████████| 10/10 [00:08<00:00,  1.13it/s]
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/peft/tuners/lora/layer.py:595: UserWarning: Already unmerged. Nothing to do.
warnings.warn("Already unmerged. Nothing to do.")
/root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/peft/tuners/lora/layer.py:256: UserWarning: Already unmerged. Nothing to do.
warnings.warn("Already unmerged. Nothing to do.")

Version Details

Version ID: a69b948db098683030b614504f7375c374627604637398dc23eb99db11b33962
Version Created: March 13, 2024

Run on Replicate →