fofr/pulid-lightning 🔢📝🖼️❓ → 🖼️

▶️ 141.6K runs 📅 May 2024 ⚙️ Cog 0.9.7 🔗 GitHub 📄 Paper ⚖️ License

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

About

Use a face to instantly make images. Uses SDXL Lightning checkpoints.

Example Output

Prompt:

"A screenshot of a person in a video game, unreal engine, ps5"

Output

Performance Metrics

4.30s Prediction Time

4.34s Total Time

All Input Parameters

{
  "width": 1152,
  "height": 768,
  "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
  "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
  "face_style": "high-fidelity",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "photo, photography",
  "checkpoint_model": "artistic",
  "number_of_images": 1
}

Input Parameters

seed Type: integer: Set a seed for reproducibility. Random by default.
width Type: integerDefault: 1024: Width of the output image (ignored if structure image given)
height Type: integerDefault: 1024: Height of the output image (ignored if structure image given)
prompt Type: stringDefault: A photo of a person: You might need to include a gender in the prompt to get the desired result
face_image (required) Type: string: The face image to use for the generation
face_style Default: high-fidelity: Style of the face
output_format Default: webp: Format of the output images
output_quality Type: integerDefault: 80Range: 0 - 100: Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
negative_prompt Type: stringDefault:: Things you do not want to see in your image
checkpoint_model Default: default: Model to use for the generation
number_of_images Type: integerDefault: 1Range: 1 - 10: Number of images to generate

Output Schema

Output

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

Example Execution Logs

Random seed set to: 559882634
Checking inputs
✅ /tmp/inputs/image.png
====================================
Checking weights
✅ Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors
✅ models/antelopev2
✅ ProteusV0.4-Lighting.safetensors
✅ ip-adapter_pulid_sdxl_fp16.safetensors
✅ dreamshaperXL_lightningDPMSDE.safetensors
====================================
Running workflow
got prompt
Executing node 3, title: KSampler, class type: KSampler
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.18it/s]
 50%|█████     | 2/4 [00:00<00:00,  2.09it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  2.14it/s]
100%|██████████| 4/4 [00:01<00:00,  2.73it/s]
100%|██████████| 4/4 [00:01<00:00,  2.47it/s]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 47, title: Save Image, class type: SaveImage
Prompt executed in 1.95 seconds
outputs:  {'47': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png

Version Details

Version ID: a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382
Version Created: May 9, 2024

Run on Replicate →