ckizer/ckizer-64 🖼️🔢❓📝✓ → 🖼️

▶️ 388 runs 📅 Sep 2024 ⚙️ Cog 0.9.20
lora lora-person text-to-image

About

This model generates photo portraits of Court Kizer. Use the trigger word "ckizer" in your prompt. EX: "A professional portrait photo of ckizer, in a tech office in California"

Example Output

Prompt:

"a portrait of ckizer a human man sitting on a porch swing in a screened in patio, beautiful lighting"

Output

Example outputExample outputExample outputExample output

Performance Metrics

65.29s Prediction Time
78.43s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "a portrait of ckizer a human man sitting on a porch swing in a screened in patio, beautiful lighting",
  "lora_scale": 1,
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 40
}
Input Parameters
mask Type: string
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev
Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
width Type: integerRange: 256 - 1440
Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
height Type: integerRange: 256 - 1440
Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
prompt (required) Type: string
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
go_fast Type: booleanDefault: false
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
megapixels Default: 1
Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 1:1
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
replicate_weights Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

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

Example Execution Logs 
Using seed: 23147
Prompt: a portrait of ckizer a human man sitting on a porch swing in a screened in patio, beautiful lighting
txt2img mode
Using dev model
free=9422393511936
Downloading weights
2024-09-04T13:27:43Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpczni2c48/weights url=https://replicate.delivery/yhqm/Sb6AbPuwFbrGGlFxtCD965mrg7SeQXDDoPWfIrKQq5d26gZTA/trained_model.tar
2024-09-04T13:27:47Z | INFO  | [ Complete ] dest=/tmp/tmpczni2c48/weights size="172 MB" total_elapsed=3.448s url=https://replicate.delivery/yhqm/Sb6AbPuwFbrGGlFxtCD965mrg7SeQXDDoPWfIrKQq5d26gZTA/trained_model.tar
Downloaded weights in 3.48s
Loaded LoRAs in 21.58s
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:01<00:40,  1.05s/it]
  5%|▌         | 2/40 [00:01<00:35,  1.08it/s]
  8%|▊         | 3/40 [00:02<00:36,  1.02it/s]
 10%|█         | 4/40 [00:03<00:36,  1.01s/it]
 12%|█▎        | 5/40 [00:05<00:35,  1.02s/it]
 15%|█▌        | 6/40 [00:06<00:35,  1.03s/it]
 18%|█▊        | 7/40 [00:07<00:34,  1.04s/it]
 20%|██        | 8/40 [00:08<00:33,  1.05s/it]
 22%|██▎       | 9/40 [00:09<00:32,  1.05s/it]
 25%|██▌       | 10/40 [00:10<00:31,  1.05s/it]
 28%|██▊       | 11/40 [00:11<00:30,  1.05s/it]
 30%|███       | 12/40 [00:12<00:29,  1.05s/it]
 32%|███▎      | 13/40 [00:13<00:28,  1.05s/it]
 35%|███▌      | 14/40 [00:14<00:27,  1.05s/it]
 38%|███▊      | 15/40 [00:15<00:26,  1.05s/it]
 40%|████      | 16/40 [00:16<00:25,  1.06s/it]
 42%|████▎     | 17/40 [00:17<00:24,  1.06s/it]
 45%|████▌     | 18/40 [00:18<00:23,  1.06s/it]
 48%|████▊     | 19/40 [00:19<00:22,  1.06s/it]
 50%|█████     | 20/40 [00:20<00:21,  1.06s/it]
 52%|█████▎    | 21/40 [00:21<00:20,  1.06s/it]
 55%|█████▌    | 22/40 [00:22<00:19,  1.06s/it]
 57%|█████▊    | 23/40 [00:24<00:17,  1.06s/it]
 60%|██████    | 24/40 [00:25<00:16,  1.06s/it]
 62%|██████▎   | 25/40 [00:26<00:15,  1.06s/it]
 65%|██████▌   | 26/40 [00:27<00:14,  1.06s/it]
 68%|██████▊   | 27/40 [00:28<00:13,  1.05s/it]
 70%|███████   | 28/40 [00:29<00:12,  1.06s/it]
 72%|███████▎  | 29/40 [00:30<00:11,  1.06s/it]
 75%|███████▌  | 30/40 [00:31<00:10,  1.06s/it]
 78%|███████▊  | 31/40 [00:32<00:09,  1.06s/it]
 80%|████████  | 32/40 [00:33<00:08,  1.06s/it]
 82%|████████▎ | 33/40 [00:34<00:07,  1.06s/it]
 85%|████████▌ | 34/40 [00:35<00:06,  1.06s/it]
 88%|████████▊ | 35/40 [00:36<00:05,  1.06s/it]
 90%|█████████ | 36/40 [00:37<00:04,  1.05s/it]
 92%|█████████▎| 37/40 [00:38<00:03,  1.05s/it]
 95%|█████████▌| 38/40 [00:39<00:02,  1.06s/it]
 98%|█████████▊| 39/40 [00:40<00:01,  1.06s/it]
100%|██████████| 40/40 [00:42<00:00,  1.06s/it]
100%|██████████| 40/40 [00:42<00:00,  1.05s/it]
Version Details
Version ID
b48db8cd39b088807800d7e7235024d116b9b1bd1fc2b8e1689b32743aae7b6c
Version Created
September 4, 2024
Run on Replicate →