killjasper/jazzclone 🖼️🔢❓📝✓ → 🖼️

▶️ 28 runs 📅 Sep 2025 ⚙️ Cog 0.13.6
lora lora-person text-to-image

About

Example Output

Prompt:

"

Professional graduation portrait photography of jazzclone wearing traditional black academic regalia including a black graduation gown with emerald green hood lining and gold trim accents, black mortarboard cap with tassel held playfully in right hand at face level, sitting in relaxed three-quarter pose against a mottled blue studio backdrop with subtle texture variations from light to medium blue tones. Subject is smiling warmly at camera, wearing a white dress shirt visible at collar, gold wristwatch on left wrist. Professional studio lighting creating soft shadows, formal academic portrait style. Use model: jazzclone for face and body. High resolution, sharp focus, professional graduation photo aesthetic, subtle vignetting at edges."
Key details to ensure accuracy:

Specify the exact pose (seated, three-quarter angle)
Note the specific colors (emerald green hood, gold trim)
Mention the playful gesture with the tassel
Include the backdrop texture and color gradient
Specify professional studio lighting
Add "jazzclone" as the model reference for the face/body swap
Include details like the watch and visible white shirt collar for authenticity

"

Output

Example output

Performance Metrics

8.35s Prediction Time
8.48s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "Professional graduation portrait photography of jazzclone wearing traditional black academic regalia including a black graduation gown with emerald green hood lining and gold trim accents, black mortarboard cap with tassel held playfully in right hand at face level, sitting in relaxed three-quarter pose against a mottled blue studio backdrop with subtle texture variations from light to medium blue tones. Subject is smiling warmly at camera, wearing a white dress shirt visible at collar, gold wristwatch on left wrist. Professional studio lighting creating soft shadows, formal academic portrait style. Use model: jazzclone for face and body. High resolution, sharp focus, professional graduation photo aesthetic, subtle vignetting at edges.\"\nKey details to ensure accuracy:\n\nSpecify the exact pose (seated, three-quarter angle)\nNote the specific colors (emerald green hood, gold trim)\nMention the playful gesture with the tassel\nInclude the backdrop texture and color gradient\nSpecify professional studio lighting\nAdd \"jazzclone\" as the model reference for the face/body swap\nInclude details like the watch and visible white shirt collar for authenticity",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}
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 
free=23563867025408
Downloading weights
2025-09-09T00:40:22Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp_98_y4he/weights url=https://replicate.delivery/xezq/XXam4lZMGzbgLp1bPul3n33HU0sRLfk4Gdfl9vLLLhGMlrSVA/flux-lora.tar
2025-09-09T00:40:22Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-09-09T00:40:22Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/XXam4lZMGzbgLp1bPul3n33HU0sRLfk4Gdfl9vLLLhGMlrSVA/flux-lora.tar url=https://replicate.delivery/xezq/XXam4lZMGzbgLp1bPul3n33HU0sRLfk4Gdfl9vLLLhGMlrSVA/flux-lora.tar
2025-09-09T00:40:22Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/602a18613706cda71171a5d711a0786c00977f575f54978098c665f92fad4982?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250909%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250909T004022Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=7cd1be0287dd182551c695283c30d0c9333cdc004a4d95cdbed8771a9ac07da6 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/XXam4lZMGzbgLp1bPul3n33HU0sRLfk4Gdfl9vLLLhGMlrSVA/flux-lora.tar
2025-09-09T00:40:22Z | INFO  | [ Complete ] dest=/tmp/tmp_98_y4he/weights size="172 MB" total_elapsed=0.235s url=https://replicate.delivery/xezq/XXam4lZMGzbgLp1bPul3n33HU0sRLfk4Gdfl9vLLLhGMlrSVA/flux-lora.tar
Downloaded weights in 0.29s
Loaded LoRAs in 0.79s
Using seed: 53947
Prompt: Professional graduation portrait photography of jazzclone wearing traditional black academic regalia including a black graduation gown with emerald green hood lining and gold trim accents, black mortarboard cap with tassel held playfully in right hand at face level, sitting in relaxed three-quarter pose against a mottled blue studio backdrop with subtle texture variations from light to medium blue tones. Subject is smiling warmly at camera, wearing a white dress shirt visible at collar, gold wristwatch on left wrist. Professional studio lighting creating soft shadows, formal academic portrait style. Use model: jazzclone for face and body. High resolution, sharp focus, professional graduation photo aesthetic, subtle vignetting at edges."
Key details to ensure accuracy:
Specify the exact pose (seated, three-quarter angle)
Note the specific colors (emerald green hood, gold trim)
Mention the playful gesture with the tassel
Include the backdrop texture and color gradient
Specify professional studio lighting
Add "jazzclone" as the model reference for the face/body swap
Include details like the watch and visible white shirt collar for authenticity
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:07,  3.80it/s]
  7%|▋         | 2/28 [00:00<00:06,  4.31it/s]
 11%|█         | 3/28 [00:00<00:06,  4.07it/s]
 14%|█▍        | 4/28 [00:00<00:06,  3.97it/s]
 18%|█▊        | 5/28 [00:01<00:05,  3.91it/s]
 21%|██▏       | 6/28 [00:01<00:05,  3.88it/s]
 25%|██▌       | 7/28 [00:01<00:05,  3.86it/s]
 29%|██▊       | 8/28 [00:02<00:05,  3.84it/s]
 32%|███▏      | 9/28 [00:02<00:04,  3.84it/s]
 36%|███▌      | 10/28 [00:02<00:04,  3.83it/s]
 39%|███▉      | 11/28 [00:02<00:04,  3.82it/s]
 43%|████▎     | 12/28 [00:03<00:04,  3.82it/s]
 46%|████▋     | 13/28 [00:03<00:03,  3.82it/s]
 50%|█████     | 14/28 [00:03<00:03,  3.82it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  3.82it/s]
 57%|█████▋    | 16/28 [00:04<00:03,  3.82it/s]
 61%|██████    | 17/28 [00:04<00:02,  3.82it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  3.82it/s]
 68%|██████▊   | 19/28 [00:04<00:02,  3.82it/s]
 71%|███████▏  | 20/28 [00:05<00:02,  3.82it/s]
 75%|███████▌  | 21/28 [00:05<00:01,  3.82it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  3.82it/s]
 82%|████████▏ | 23/28 [00:05<00:01,  3.82it/s]
 86%|████████▌ | 24/28 [00:06<00:01,  3.82it/s]
 89%|████████▉ | 25/28 [00:06<00:00,  3.82it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  3.82it/s]
 96%|█████████▋| 27/28 [00:07<00:00,  3.82it/s]
100%|██████████| 28/28 [00:07<00:00,  3.82it/s]
100%|██████████| 28/28 [00:07<00:00,  3.85it/s]
Total safe images: 1 out of 1
Version Details
Version ID
08e53c0d00d489b1cbc296b43a1b0cfcae655a5bed3917ec172f1a629dd2761c
Version Created
September 7, 2025
Run on Replicate →