chickenortheeggapp/grandma-aiavatar 🖼️🔢❓📝✓ → 🖼️

▶️ 68 runs 📅 Aug 2026 ⚙️ Cog 0.15.3
lora lora-person text-to-image

Performance

25.9sTypical run time
68Total runs

About

Example Output

Prompt:

"A photorealistic 16:9 outdoor editorial portrait of GRANDMA_TRIGGER, a warm, intelligent, approachable woman in her early fifties. She has naturally aging skin with soft fine lines, bright dark brown eyes, long wavy gray brown hair with gentle silver streaks, and a kind, reassuring smile. Her expression is friendly, supportive, practical, and quietly humorous.
She stands in a lush green homestead yard at sunrise, surrounded by soft golden light. The background features a beautifully maintained classic white wooden chicken coop with natural wood trim, set slightly out of focus. The yard is vibrant and peaceful, with tall grasses, soft greenery, and warm natural textures.
Clothing: loose‑fitting boho homestead style inspired by the real wardrobe. A muted dusty‑blue top, layered with a warm beige or natural‑tone soft flannels featuring subtle chicken or feather embroidery. Earthy brown accents, comfortable textures, natural fabrics. Dark blue and dusty blue are focus colors. Soft layered necklines, short necklines. Glasses and hair design consistent with her real appearance.
Lighting: soft golden sunrise light from the side, balanced with natural ambient outdoor light. Realistic skin texture, soft glam up natural makeup, detailed brown eyes with long dark eyelashes, believably long soft, thick, wavy, hair strands, accurate hands, gentle color grading, shallow depth of field, crisp facial focus, ordinary background bokeh. Careful focus on the necklines ensure the neck is short and realistic; collarbone is short and blended naturally into neck area. Neck, jaw, and upper chest area should look natural, properly shadowed, and softly blended. accurate hands, gentle color grading, shallow depth of field, crisp facial focus, natural background bokeh.
Tone: calm, cozy, trustworthy Chicken Care atmosphere. Natural makeup appropriate for her age, clean white teeth, uncluttered environment.
Composition: wide 16:9 layout with generous negative space on both sides for future captions. Face, hair, shoulders, hands, and clothing unobstructed."

Output

Example outputExample outputExample output

Performance Metrics

25.90s Prediction Time
38.09s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "A photorealistic 16:9 outdoor editorial portrait of GRANDMA_TRIGGER, a warm, intelligent, approachable woman in her early fifties. She has naturally aging skin with soft fine lines, bright dark brown eyes, long wavy gray brown hair with gentle silver streaks, and a kind, reassuring smile. Her expression is friendly, supportive, practical, and quietly humorous.\nShe stands in a lush green homestead yard at sunrise, surrounded by soft golden light. The background features a beautifully maintained classic white wooden chicken coop with natural wood trim, set slightly out of focus. The yard is vibrant and peaceful, with tall grasses, soft greenery, and warm natural textures.\nClothing: loose‑fitting boho homestead style inspired by the real wardrobe. A muted dusty‑blue top, layered with a warm beige or natural‑tone soft flannels featuring subtle chicken or feather embroidery. Earthy brown accents, comfortable textures, natural fabrics. Dark blue and dusty blue are focus colors. Soft layered necklines, short necklines. Glasses and hair design consistent with her real appearance.\nLighting: soft golden sunrise light from the side, balanced with natural ambient outdoor light. Realistic skin texture, soft glam up natural makeup, detailed brown eyes with long dark eyelashes, believably long soft, thick, wavy, hair strands, accurate hands, gentle color grading, shallow depth of field, crisp facial focus, ordinary background bokeh. Careful focus on the necklines ensure the neck is short and realistic; collarbone is short and blended naturally into neck area. Neck, jaw, and upper chest area should look natural, properly shadowed, and softly blended. accurate hands, gentle color grading, shallow depth of field, crisp facial focus, natural background bokeh.\nTone: calm, cozy, trustworthy Chicken Care atmosphere. Natural makeup appropriate for her age, clean white teeth, uncluttered environment.\nComposition: wide 16:9 layout with generous negative space on both sides for future captions. Face, hair, shoulders, hands, and clothing unobstructed.\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 3,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "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=19865521954816
Downloading weights
2026-08-06T23:03:42Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpmpne_qva/weights url=https://replicate.delivery/xezq/9DAMQk77l1ZZEdiQ5T4nkvonfe2XtPNVIdyWM6mmxhm4iYAXA/trained_model.tar
2026-08-06T23:03:42Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2026-08-06T23:03:42Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/9DAMQk77l1ZZEdiQ5T4nkvonfe2XtPNVIdyWM6mmxhm4iYAXA/trained_model.tar url=https://replicate.delivery/xezq/9DAMQk77l1ZZEdiQ5T4nkvonfe2XtPNVIdyWM6mmxhm4iYAXA/trained_model.tar
2026-08-06T23:03:42Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric2.cwlota.com/c4d05a9ca08a7dfbea240d4805fca13d279cfb50aa4ab117c564f603bf995708?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWVOGIYODJJPRECK%2F20260806%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20260806T230342Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=1fb25a1586a068faedeaa04783a70a2ea10ae7eae52278de1f9c03769291089d url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/9DAMQk77l1ZZEdiQ5T4nkvonfe2XtPNVIdyWM6mmxhm4iYAXA/trained_model.tar
2026-08-06T23:03:43Z | INFO  | [ Complete ] dest=/tmp/tmpmpne_qva/weights size="172 MB" total_elapsed=0.527s url=https://replicate.delivery/xezq/9DAMQk77l1ZZEdiQ5T4nkvonfe2XtPNVIdyWM6mmxhm4iYAXA/trained_model.tar
Downloaded weights in 0.59s
Loaded LoRAs in 1.19s
Using seed: 50387
Prompt: A photorealistic 16:9 outdoor editorial portrait of GRANDMA_TRIGGER, a warm, intelligent, approachable woman in her early fifties. She has naturally aging skin with soft fine lines, bright dark brown eyes, long wavy gray brown hair with gentle silver streaks, and a kind, reassuring smile. Her expression is friendly, supportive, practical, and quietly humorous.
She stands in a lush green homestead yard at sunrise, surrounded by soft golden light. The background features a beautifully maintained classic white wooden chicken coop with natural wood trim, set slightly out of focus. The yard is vibrant and peaceful, with tall grasses, soft greenery, and warm natural textures.
Clothing: loose‑fitting boho homestead style inspired by the real wardrobe. A muted dusty‑blue top, layered with a warm beige or natural‑tone soft flannels featuring subtle chicken or feather embroidery. Earthy brown accents, comfortable textures, natural fabrics. Dark blue and dusty blue are focus colors. Soft layered necklines, short necklines. Glasses and hair design consistent with her real appearance.
Lighting: soft golden sunrise light from the side, balanced with natural ambient outdoor light. Realistic skin texture, soft glam up natural makeup, detailed brown eyes with long dark eyelashes, believably long soft, thick, wavy, hair strands, accurate hands, gentle color grading, shallow depth of field, crisp facial focus, ordinary background bokeh. Careful focus on the necklines ensure the neck is short and realistic; collarbone is short and blended naturally into neck area. Neck, jaw, and upper chest area should look natural, properly shadowed, and softly blended. accurate hands, gentle color grading, shallow depth of field, crisp facial focus, natural background bokeh.
Tone: calm, cozy, trustworthy Chicken Care atmosphere. Natural makeup appropriate for her age, clean white teeth, uncluttered environment.
Composition: wide 16:9 layout with generous negative space on both sides for future captions. Face, hair, shoulders, hands, and clothing unobstructed.
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:19,  1.38it/s]
  7%|▋         | 2/28 [00:01<00:16,  1.55it/s]
 11%|█         | 3/28 [00:02<00:17,  1.46it/s]
 14%|█▍        | 4/28 [00:02<00:16,  1.42it/s]
 18%|█▊        | 5/28 [00:03<00:16,  1.40it/s]
 21%|██▏       | 6/28 [00:04<00:15,  1.39it/s]
 25%|██▌       | 7/28 [00:04<00:15,  1.38it/s]
 29%|██▊       | 8/28 [00:05<00:14,  1.37it/s]
 32%|███▏      | 9/28 [00:06<00:13,  1.37it/s]
 36%|███▌      | 10/28 [00:07<00:13,  1.37it/s]
 39%|███▉      | 11/28 [00:07<00:12,  1.36it/s]
 43%|████▎     | 12/28 [00:08<00:11,  1.36it/s]
 46%|████▋     | 13/28 [00:09<00:11,  1.36it/s]
 50%|█████     | 14/28 [00:10<00:10,  1.36it/s]
 54%|█████▎    | 15/28 [00:10<00:09,  1.36it/s]
 57%|█████▋    | 16/28 [00:11<00:08,  1.36it/s]
 61%|██████    | 17/28 [00:12<00:08,  1.36it/s]
 64%|██████▍   | 18/28 [00:13<00:07,  1.36it/s]
 68%|██████▊   | 19/28 [00:13<00:06,  1.36it/s]
 71%|███████▏  | 20/28 [00:14<00:05,  1.36it/s]
 75%|███████▌  | 21/28 [00:15<00:05,  1.36it/s]
 79%|███████▊  | 22/28 [00:16<00:04,  1.36it/s]
 82%|████████▏ | 23/28 [00:16<00:03,  1.36it/s]
 86%|████████▌ | 24/28 [00:17<00:02,  1.36it/s]
 89%|████████▉ | 25/28 [00:18<00:02,  1.36it/s]
 93%|█████████▎| 26/28 [00:18<00:01,  1.36it/s]
 96%|█████████▋| 27/28 [00:19<00:00,  1.36it/s]
100%|██████████| 28/28 [00:20<00:00,  1.36it/s]
100%|██████████| 28/28 [00:20<00:00,  1.37it/s]
Total safe images: 3 out of 3
Version Details
Version ID
4c2b7c11de22b82bbc839f5d625892f601dfb4bb2a4a984db1e0d9f30f24a892
Version Created
August 6, 2026
Run on Replicate →