mayoita/avata 🖼️🔢❓📝✓ → 🖼️

▶️ 14 runs 📅 Jul 2025 ⚙️ Cog 0.15.3

About

Example Output

Prompt:

"A beautiful ava with tight hair show ear in a black dress, in the style of Helmut Newton. The soft lighting creates a portrait with a dynamic pose. The black-and-white image has a grainy texture, captured with a vintage film camera and large-format analog lens."

Output

Performance Metrics

13.76s Prediction Time

13.84s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A beautiful ava with tight hair show ear in a black dress, in the style of Helmut Newton. The soft lighting creates a portrait with a dynamic pose. The black-and-white image has a grainy texture, captured with a vintage film camera and large-format analog lens.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2.79,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 48
}

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=23567089721344
Downloading weights
2025-07-19T22:22:37Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpj1teat5b/weights url=https://replicate.delivery/xezq/ecrcti8veYi2tEcWcpMHe2DJ17846ZyeypmFe3ZjAoaGglToC/trained_model.tar
2025-07-19T22:22:37Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-19T22:22:37Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/ecrcti8veYi2tEcWcpMHe2DJ17846ZyeypmFe3ZjAoaGglToC/trained_model.tar url=https://replicate.delivery/xezq/ecrcti8veYi2tEcWcpMHe2DJ17846ZyeypmFe3ZjAoaGglToC/trained_model.tar
2025-07-19T22:22:37Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/b6025a6996a60d1a9509e42f501cfef5a2a1b34c666487b570c2368e2884d590?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250719%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250719T222237Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=01d2f1e1fe195b26b1149f67a1acd5bd0656b76972ee1514e853c43236df3567 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/ecrcti8veYi2tEcWcpMHe2DJ17846ZyeypmFe3ZjAoaGglToC/trained_model.tar
2025-07-19T22:22:38Z | INFO  | [ Complete ] dest=/tmp/tmpj1teat5b/weights size="172 MB" total_elapsed=0.281s url=https://replicate.delivery/xezq/ecrcti8veYi2tEcWcpMHe2DJ17846ZyeypmFe3ZjAoaGglToC/trained_model.tar
Downloaded weights in 0.34s
Loaded LoRAs in 0.94s
Using seed: 55088
Prompt: A beautiful ava with tight hair show ear in a black dress, in the style of Helmut Newton. The soft lighting creates a portrait with a dynamic pose. The black-and-white image has a grainy texture, captured with a vintage film camera and large-format analog lens.
[!] txt2img mode
  0%|          | 0/48 [00:00<?, ?it/s]
  2%|▏         | 1/48 [00:00<00:12,  3.82it/s]
  4%|▍         | 2/48 [00:00<00:10,  4.33it/s]
  6%|▋         | 3/48 [00:00<00:11,  4.09it/s]
  8%|▊         | 4/48 [00:00<00:11,  3.98it/s]
 10%|█         | 5/48 [00:01<00:10,  3.92it/s]
 12%|█▎        | 6/48 [00:01<00:10,  3.88it/s]
 15%|█▍        | 7/48 [00:01<00:10,  3.86it/s]
 17%|█▋        | 8/48 [00:02<00:10,  3.85it/s]
 19%|█▉        | 9/48 [00:02<00:10,  3.84it/s]
 21%|██        | 10/48 [00:02<00:09,  3.83it/s]
 23%|██▎       | 11/48 [00:02<00:09,  3.82it/s]
 25%|██▌       | 12/48 [00:03<00:09,  3.82it/s]
 27%|██▋       | 13/48 [00:03<00:09,  3.82it/s]
 29%|██▉       | 14/48 [00:03<00:08,  3.81it/s]
 31%|███▏      | 15/48 [00:03<00:08,  3.82it/s]
 33%|███▎      | 16/48 [00:04<00:08,  3.81it/s]
 35%|███▌      | 17/48 [00:04<00:08,  3.82it/s]
 38%|███▊      | 18/48 [00:04<00:07,  3.82it/s]
 40%|███▉      | 19/48 [00:04<00:07,  3.81it/s]
 42%|████▏     | 20/48 [00:05<00:07,  3.81it/s]
 44%|████▍     | 21/48 [00:05<00:07,  3.81it/s]
 46%|████▌     | 22/48 [00:05<00:06,  3.81it/s]
 48%|████▊     | 23/48 [00:05<00:06,  3.81it/s]
 50%|█████     | 24/48 [00:06<00:06,  3.81it/s]
 52%|█████▏    | 25/48 [00:06<00:06,  3.81it/s]
 54%|█████▍    | 26/48 [00:06<00:05,  3.81it/s]
 56%|█████▋    | 27/48 [00:07<00:05,  3.80it/s]
 58%|█████▊    | 28/48 [00:07<00:05,  3.80it/s]
 60%|██████    | 29/48 [00:07<00:04,  3.81it/s]
 62%|██████▎   | 30/48 [00:07<00:04,  3.81it/s]
 65%|██████▍   | 31/48 [00:08<00:04,  3.81it/s]
 67%|██████▋   | 32/48 [00:08<00:04,  3.81it/s]
 69%|██████▉   | 33/48 [00:08<00:03,  3.81it/s]
 71%|███████   | 34/48 [00:08<00:03,  3.81it/s]
 73%|███████▎  | 35/48 [00:09<00:03,  3.81it/s]
 75%|███████▌  | 36/48 [00:09<00:03,  3.81it/s]
 77%|███████▋  | 37/48 [00:09<00:02,  3.82it/s]
 79%|███████▉  | 38/48 [00:09<00:02,  3.81it/s]
 81%|████████▏ | 39/48 [00:10<00:02,  3.81it/s]
 83%|████████▎ | 40/48 [00:10<00:02,  3.81it/s]
 85%|████████▌ | 41/48 [00:10<00:01,  3.81it/s]
 88%|████████▊ | 42/48 [00:10<00:01,  3.81it/s]
 90%|████████▉ | 43/48 [00:11<00:01,  3.81it/s]
 92%|█████████▏| 44/48 [00:11<00:01,  3.81it/s]
 94%|█████████▍| 45/48 [00:11<00:00,  3.82it/s]
 96%|█████████▌| 46/48 [00:12<00:00,  3.82it/s]
 98%|█████████▊| 47/48 [00:12<00:00,  3.82it/s]
100%|██████████| 48/48 [00:12<00:00,  3.82it/s]
100%|██████████| 48/48 [00:12<00:00,  3.83it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 4bc77c2f4e6ed34903377ba2894bb6fab78589c7db00204d1e6f19a7d572611b
Version Created: July 19, 2025

Run on Replicate →