autom8tion/jefflong 🖼️🔢❓📝✓ → 🖼️

▶️ 67 runs 📅 Jun 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"A hyper-realistic portrait of JEFF standing in front of a glowing AI dashboard, wearing a MailBot-branded hoodie.
His arms are crossed, and holographic emails float past him.
The scene has deep contrast, dramatic lighting, and a clean tech vibe."

Output

Performance Metrics

3.51s Prediction Time

3.88s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A hyper-realistic portrait of JEFF standing in front of a glowing AI dashboard, wearing a MailBot-branded hoodie.\nHis arms are crossed, and holographic emails float past him.\nThe scene has deep contrast, dramatic lighting, and a clean tech vibe.",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "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=25876845899776
Downloading weights
2025-06-30T08:59:06Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpwkg6wokc/weights url=https://replicate.delivery/xezq/CtLo1xcCnJ4NNRwfqCTp3hOSYaVqbJ9snEmfoP60VXaG8f3pA/flux-lora.tar
2025-06-30T08:59:06Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-06-30T08:59:06Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/CtLo1xcCnJ4NNRwfqCTp3hOSYaVqbJ9snEmfoP60VXaG8f3pA/flux-lora.tar url=https://replicate.delivery/xezq/CtLo1xcCnJ4NNRwfqCTp3hOSYaVqbJ9snEmfoP60VXaG8f3pA/flux-lora.tar
2025-06-30T08:59:06Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/ac27dd3cbbb62aae57ca3b25b7c6bc5bf5583b48fbe8903e80b214c522306b8e?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250630%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250630T085906Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=9b44cc89a130803273d769d66a292991a92c6f924cfa6136f3b74594b608d391 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/CtLo1xcCnJ4NNRwfqCTp3hOSYaVqbJ9snEmfoP60VXaG8f3pA/flux-lora.tar
2025-06-30T08:59:06Z | INFO  | [ Complete ] dest=/tmp/tmpwkg6wokc/weights size="172 MB" total_elapsed=0.232s url=https://replicate.delivery/xezq/CtLo1xcCnJ4NNRwfqCTp3hOSYaVqbJ9snEmfoP60VXaG8f3pA/flux-lora.tar
Downloaded weights in 0.29s
2025-06-30 08:59:06.574 | INFO     | fp8.lora_loading:convert_lora_weights:502 - Loading LoRA weights for /src/weights-cache/0fab0fb221053310
2025-06-30 08:59:06.665 | INFO     | fp8.lora_loading:convert_lora_weights:523 - LoRA weights loaded
2025-06-30 08:59:06.666 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:610 - Extracting keys
2025-06-30 08:59:06.666 | DEBUG    | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:617 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  42%|████▏     | 127/304 [00:00<00:00, 1260.55it/s]
Applying LoRA:  84%|████████▎ | 254/304 [00:00<00:00, 1078.79it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1065.13it/s]
2025-06-30 08:59:06.952 | INFO     | fp8.lora_loading:apply_lora_to_model_and_optionally_store_clones:669 - Loading LoRA in fp8
2025-06-30 08:59:06.952 | SUCCESS  | fp8.lora_loading:load_lora:547 - LoRA applied in 0.38s
running quantized prediction
Using seed: 3774259970
  0%|          | 0/28 [00:00<?, ?it/s]
 11%|█         | 3/28 [00:00<00:01, 15.85it/s]
 18%|█▊        | 5/28 [00:00<00:01, 12.88it/s]
 25%|██▌       | 7/28 [00:00<00:01, 11.91it/s]
 32%|███▏      | 9/28 [00:00<00:01, 11.46it/s]
 39%|███▉      | 11/28 [00:00<00:01, 10.84it/s]
 46%|████▋     | 13/28 [00:01<00:01, 10.75it/s]
 54%|█████▎    | 15/28 [00:01<00:01, 10.73it/s]
 61%|██████    | 17/28 [00:01<00:01, 10.75it/s]
 68%|██████▊   | 19/28 [00:01<00:00, 10.72it/s]
 75%|███████▌  | 21/28 [00:01<00:00, 10.59it/s]
 82%|████████▏ | 23/28 [00:02<00:00, 10.54it/s]
 89%|████████▉ | 25/28 [00:02<00:00, 10.57it/s]
 96%|█████████▋| 27/28 [00:02<00:00, 10.61it/s]
100%|██████████| 28/28 [00:02<00:00, 10.97it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 8915662f447893c5f4c4c02a96a23a30116c3fca57f2c25ef8789fc753fb1255
Version Created: June 30, 2025

Run on Replicate →