marinasmile333/my-avatar-lora 🖼️🔢❓📝✓ → 🖼️

▶️ 197 runs 📅 Oct 2025 ⚙️ Cog 0.15.3
lora lora-person text-to-image

Performance

28.0sTypical run time
197Total runs

About

Example Output

Prompt:

"Warm, cinematic portrait of myavatar honey blonde gorgeous woman with perfect turquoise eyes sitting comfortably on a plush sofa in a cozy, tastefully decorated living room, surrounded by soft, diffused light from a nearby fireplace. [Your LoRA Avatar] is looking gently towards an empty space next to them, with a warm, inviting smile, as if expecting or acknowledging a loved one's presence. There are subtle details like a half-drunk cup of tea and an open book on a coffee table"

Output

Example outputExample outputExample outputExample output

Performance Metrics

27.98s Prediction Time
28.01s Total Time
All Input Parameters 
{
  "model": "dev",
  "width": 1087,
  "height": 1440,
  "prompt": "Warm, cinematic portrait of myavatar  honey blonde gorgeous woman with perfect turquoise eyes sitting comfortably on a plush sofa in a cozy, tastefully decorated living room, surrounded by soft, diffused light from a nearby fireplace. [Your LoRA Avatar] is looking gently towards an empty space next to them, with a warm, inviting smile, as if expecting or acknowledging a loved one's presence. There are subtle details like a half-drunk cup of tea and an open book on a coffee table",
  "go_fast": false,
  "lora_scale": 1.2,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "jpg",
  "guidance_scale": 10,
  "output_quality": 80,
  "prompt_strength": 0.4,
  "extra_lora_scale": 0.5,
  "num_inference_steps": 25
}
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=26874440036352
Downloading weights
2025-10-21T00:25:48Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpnghoq_m0/weights url=https://replicate.delivery/xezq/NaWKmjQdDdbEG1UHqGedxuy0b4l0SrexQ7xwzZdaylwFnTgVA/trained_model.tar
2025-10-21T00:25:48Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-10-21T00:25:48Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/NaWKmjQdDdbEG1UHqGedxuy0b4l0SrexQ7xwzZdaylwFnTgVA/trained_model.tar url=https://replicate.delivery/xezq/NaWKmjQdDdbEG1UHqGedxuy0b4l0SrexQ7xwzZdaylwFnTgVA/trained_model.tar
2025-10-21T00:25:48Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/625c2bb558d4745846d9cb638eb355567112994fc7c137e822e6964228087b80?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20251021%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20251021T002548Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=43a7d9057edd4f42eefbf6fa17860581a73bae343d78bcdac28d956f4631b273 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/NaWKmjQdDdbEG1UHqGedxuy0b4l0SrexQ7xwzZdaylwFnTgVA/trained_model.tar
2025-10-21T00:25:49Z | INFO  | [ Complete ] dest=/tmp/tmpnghoq_m0/weights size="172 MB" total_elapsed=0.313s url=https://replicate.delivery/xezq/NaWKmjQdDdbEG1UHqGedxuy0b4l0SrexQ7xwzZdaylwFnTgVA/trained_model.tar
Downloaded weights in 0.38s
Loaded LoRAs in 0.94s
Using seed: 24079
Prompt: Warm, cinematic portrait of myavatar  honey blonde gorgeous woman with perfect turquoise eyes sitting comfortably on a plush sofa in a cozy, tastefully decorated living room, surrounded by soft, diffused light from a nearby fireplace. [Your LoRA Avatar] is looking gently towards an empty space next to them, with a warm, inviting smile, as if expecting or acknowledging a loved one's presence. There are subtle details like a half-drunk cup of tea and an open book on a coffee table
[!] txt2img mode
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:00<00:23,  1.04it/s]
  8%|▊         | 2/25 [00:01<00:19,  1.16it/s]
 12%|█▏        | 3/25 [00:02<00:19,  1.10it/s]
 16%|█▌        | 4/25 [00:03<00:19,  1.08it/s]
 20%|██        | 5/25 [00:04<00:18,  1.06it/s]
 24%|██▍       | 6/25 [00:05<00:18,  1.05it/s]
 28%|██▊       | 7/25 [00:06<00:17,  1.05it/s]
 32%|███▏      | 8/25 [00:07<00:16,  1.04it/s]
 36%|███▌      | 9/25 [00:08<00:15,  1.04it/s]
 40%|████      | 10/25 [00:09<00:14,  1.04it/s]
 44%|████▍     | 11/25 [00:10<00:13,  1.04it/s]
 48%|████▊     | 12/25 [00:11<00:12,  1.04it/s]
 52%|█████▏    | 13/25 [00:12<00:11,  1.04it/s]
 56%|█████▌    | 14/25 [00:13<00:10,  1.04it/s]
 60%|██████    | 15/25 [00:14<00:09,  1.04it/s]
 64%|██████▍   | 16/25 [00:15<00:08,  1.04it/s]
 68%|██████▊   | 17/25 [00:16<00:07,  1.04it/s]
 72%|███████▏  | 18/25 [00:17<00:06,  1.04it/s]
 76%|███████▌  | 19/25 [00:18<00:05,  1.04it/s]
 80%|████████  | 20/25 [00:19<00:04,  1.03it/s]
 84%|████████▍ | 21/25 [00:20<00:03,  1.04it/s]
 88%|████████▊ | 22/25 [00:21<00:02,  1.04it/s]
 92%|█████████▏| 23/25 [00:22<00:01,  1.04it/s]
 96%|█████████▌| 24/25 [00:22<00:00,  1.04it/s]
100%|██████████| 25/25 [00:23<00:00,  1.04it/s]
100%|██████████| 25/25 [00:23<00:00,  1.04it/s]
Total safe images: 4 out of 4
Version Details
Version ID
f6a3829d41782050d35c2539a72aa91bfa0c6eb55d92af9019df50aaaf7cf585
Version Created
October 18, 2025
Run on Replicate →