clovisviana-debug/mrclovis-lora 🖼️🔢❓📝✓ → 🖼️

▶️ 39 runs 📅 Oct 2025 ⚙️ Cog 0.15.3
image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"A depiction of the demigod at rest, sprawled heroically across a bright colour velvet chaise atop Mount Olympus. Bathed in divine golden light and framed by a backdrop straight from a suburban photo studio, mrclovis looking to the eyes of the viewer with the timeless gaze of a man who knows he looks magnificent. Art historians describe this piece as equal parts Greek mythology and mall glamour"

Output

Example output

Performance Metrics

9.45s Prediction Time
14.96s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "A depiction of the demigod at rest, sprawled heroically across a bright colour velvet chaise atop Mount Olympus. Bathed in divine golden light and framed by a backdrop straight from a suburban photo studio, mrclovis  looking to the eyes of the viewer with the timeless gaze of a man who knows he looks magnificent. Art historians describe this piece as equal parts Greek mythology and mall glamour",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "output_format": "jpg",
  "guidance_scale": 2,
  "output_quality": 80,
  "prompt_strength": 1,
  "extra_lora_scale": 1,
  "num_inference_steps": 30
}
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: arrayItems Type: stringItems Format: uri

Example Execution Logs
free=24108889808896
Downloading weights
2025-10-12T07:22:30Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmprtkfty29/weights url=https://replicate.delivery/xezq/Hnftchf8yNn6bk1tyGTHGeejCRxBBGLS73qCu3mBV8i6Oo4VB/trained_model.tar
2025-10-12T07:22:30Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-10-12T07:22:30Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Hnftchf8yNn6bk1tyGTHGeejCRxBBGLS73qCu3mBV8i6Oo4VB/trained_model.tar url=https://replicate.delivery/xezq/Hnftchf8yNn6bk1tyGTHGeejCRxBBGLS73qCu3mBV8i6Oo4VB/trained_model.tar
2025-10-12T07:22:30Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/e937d6f07c0f2dcd1cc01358f83a7362337c69afb0384780b122f0b0a25bd58b?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20251012%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20251012T072230Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=ecf87d73c4c444165d679cb70e1311c317026d33db6406e1d2650992db2a02f5 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/Hnftchf8yNn6bk1tyGTHGeejCRxBBGLS73qCu3mBV8i6Oo4VB/trained_model.tar
2025-10-12T07:22:30Z | INFO  | [ Complete ] dest=/tmp/tmprtkfty29/weights size="172 MB" total_elapsed=0.453s url=https://replicate.delivery/xezq/Hnftchf8yNn6bk1tyGTHGeejCRxBBGLS73qCu3mBV8i6Oo4VB/trained_model.tar
Downloaded weights in 0.52s
Loaded LoRAs in 1.49s
Using seed: 54884
Prompt: A depiction of the demigod at rest, sprawled heroically across a bright colour velvet chaise atop Mount Olympus. Bathed in divine golden light and framed by a backdrop straight from a suburban photo studio, mrclovis  looking to the eyes of the viewer with the timeless gaze of a man who knows he looks magnificent. Art historians describe this piece as equal parts Greek mythology and mall glamour
[!] txt2img mode
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.84it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.35it/s]
 10%|█         | 3/30 [00:00<00:06,  4.11it/s]
 13%|█▎        | 4/30 [00:00<00:06,  4.00it/s]
 17%|█▋        | 5/30 [00:01<00:06,  3.95it/s]
 20%|██        | 6/30 [00:01<00:06,  3.91it/s]
 23%|██▎       | 7/30 [00:01<00:05,  3.89it/s]
 27%|██▋       | 8/30 [00:02<00:05,  3.87it/s]
 30%|███       | 9/30 [00:02<00:05,  3.86it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.86it/s]
 37%|███▋      | 11/30 [00:02<00:04,  3.85it/s]
 40%|████      | 12/30 [00:03<00:04,  3.85it/s]
 43%|████▎     | 13/30 [00:03<00:04,  3.85it/s]
 47%|████▋     | 14/30 [00:03<00:04,  3.85it/s]
 50%|█████     | 15/30 [00:03<00:03,  3.85it/s]
 53%|█████▎    | 16/30 [00:04<00:03,  3.85it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  3.85it/s]
 60%|██████    | 18/30 [00:04<00:03,  3.85it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  3.85it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.85it/s]
 70%|███████   | 21/30 [00:05<00:02,  3.85it/s]
 73%|███████▎  | 22/30 [00:05<00:02,  3.85it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  3.85it/s]
 80%|████████  | 24/30 [00:06<00:01,  3.85it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  3.84it/s]
 87%|████████▋ | 26/30 [00:06<00:01,  3.85it/s]
 90%|█████████ | 27/30 [00:06<00:00,  3.85it/s]
 93%|█████████▎| 28/30 [00:07<00:00,  3.85it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  3.85it/s]
100%|██████████| 30/30 [00:07<00:00,  3.85it/s]
100%|██████████| 30/30 [00:07<00:00,  3.87it/s]
Total safe images: 1 out of 1
Version Details
Version ID
970c3e61c2398524b477e979eff17e3ae608599ab48599a71a3a48fb23d83072
Version Created
October 11, 2025
Run on Replicate →