biggpt1/olana-marz 🖼️🔢❓📝✓ → 🖼️

▶️ 169 runs 📅 Jul 2025 ⚙️ Cog 0.13.6
image-inpainting image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"Professional photoshoot of an OLN subject in an analog, retro 2000s VHS aesthetic. A cinematic portrait shot of a young woman with short hair, wearing a half-sleeve white shirt. She stands in a softly lit corridor, her back leaning against a beige wall. To her right, a staircase descends into shadow, while a window to her left lets in a warm glow of late afternoon light. The warm light casts soft shadows across her face and the wall, creating a nostalgic and moody atmosphere. The image has a subtle film grain and muted tones reminiscent of VHS and early 2000s analog photography. Captured with a 50mm lens on a Canon AE-1, shallow depth of field keeping focus on her face while the background gently blurs, enhancing the cinematic quality."

Output

Example outputExample outputExample outputExample output

Performance Metrics

64.07s Prediction Time
64.53s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "Professional photoshoot of an OLN subject in an analog, retro 2000s VHS aesthetic. A cinematic portrait shot of a young woman with short hair, wearing a half-sleeve white shirt. She stands in a softly lit corridor, her back leaning against a beige wall. To her right, a staircase descends into shadow, while a window to her left lets in a warm glow of late afternoon light. The warm light casts soft shadows across her face and the wall, creating a nostalgic and moody atmosphere. The image has a subtle film grain and muted tones reminiscent of VHS and early 2000s analog photography. Captured with a 50mm lens on a Canon AE-1, shallow depth of field keeping focus on her face while the background gently blurs, enhancing the cinematic quality.",
  "go_fast": false,
  "extra_lora": "https://civitai.com/api/download/models/1967775?type=Model&format=SafeTensor&token=3897b44086a90075dbac7bf6ba7a94ec",
  "lora_scale": 0.94,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2.15,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": -0.58,
  "num_inference_steps": 47
}
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=27982081720320
Downloading weights
2025-07-28T20:34:01Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpysyii7sn/weights url=https://replicate.delivery/xezq/1w2LsvgtQ1rKN5TUIPIVLvjqGikLXb8RD3BNsBhfOqQqZsiKA/flux-lora.tar
2025-07-28T20:34:01Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-28T20:34:01Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/1w2LsvgtQ1rKN5TUIPIVLvjqGikLXb8RD3BNsBhfOqQqZsiKA/flux-lora.tar url=https://replicate.delivery/xezq/1w2LsvgtQ1rKN5TUIPIVLvjqGikLXb8RD3BNsBhfOqQqZsiKA/flux-lora.tar
2025-07-28T20:34:01Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/534bbad90574cc00b34b856d172315da8d37512f48d119c066f137c94c00f856?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250728%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250728T203401Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=dd9b999ee948babfb6792dd8b1a64c34ee3075b98395d4b1fc8450a795b89337 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/1w2LsvgtQ1rKN5TUIPIVLvjqGikLXb8RD3BNsBhfOqQqZsiKA/flux-lora.tar
2025-07-28T20:34:02Z | INFO  | [ Complete ] dest=/tmp/tmpysyii7sn/weights size="172 MB" total_elapsed=0.701s url=https://replicate.delivery/xezq/1w2LsvgtQ1rKN5TUIPIVLvjqGikLXb8RD3BNsBhfOqQqZsiKA/flux-lora.tar
Downloaded weights in 0.76s
free=27981909045248
Downloading weights
2025-07-28T20:34:02Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/364f447bc91daa17 url=https://civitai.com/api/download/models/1967775?type=Model&format=SafeTensor&token=3897b44086a90075dbac7bf6ba7a94ec
2025-07-28T20:34:02Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-07-28T20:34:02Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/civitai.com/api/download/models/1967775?type=Model&format=SafeTensor&token=3897b44086a90075dbac7bf6ba7a94ec url=https://civitai.com/api/download/models/1967775?type=Model&format=SafeTensor&token=3897b44086a90075dbac7bf6ba7a94ec
2025-07-28T20:34:03Z | INFO  | [ Redirect ] redirect_url=https://civitai-delivery-worker-prod.5ac0637cfd0766c97916cefa3764fbdf.r2.cloudflarestorage.com/model/2703479/mvc5000V2.yx47.safetensors?X-Amz-Expires=86400&response-content-disposition=attachment%3B%20filename%3D%22MVC5000_v2.safetensors%22&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=e01358d793ad6966166af8b3064953ad/20250728/us-east-1/s3/aws4_request&X-Amz-Date=20250728T203403Z&X-Amz-SignedHeaders=host&X-Amz-Signature=cefd28e25b867ce72ebfed6afb9c7fd7bd4ce19620ef42383670a492a09e0ed0 url=http://hermes.services.svc.cluster.local/civitai.com/api/download/models/1967775?type=Model&format=SafeTensor&token=3897b44086a90075dbac7bf6ba7a94ec
2025-07-28T20:34:12Z | INFO  | [ Complete ] dest=/src/weights-cache/364f447bc91daa17 size="153 MB" total_elapsed=9.450s url=https://civitai.com/api/download/models/1967775?type=Model&format=SafeTensor&token=3897b44086a90075dbac7bf6ba7a94ec
Downloaded weights in 9.51s
Loaded LoRAs in 11.50s
Using seed: 20672
Prompt: Professional photoshoot of an OLN subject in an analog, retro 2000s VHS aesthetic. A cinematic portrait shot of a young woman with short hair, wearing a half-sleeve white shirt. She stands in a softly lit corridor, her back leaning against a beige wall. To her right, a staircase descends into shadow, while a window to her left lets in a warm glow of late afternoon light. The warm light casts soft shadows across her face and the wall, creating a nostalgic and moody atmosphere. The image has a subtle film grain and muted tones reminiscent of VHS and early 2000s analog photography. Captured with a 50mm lens on a Canon AE-1, shallow depth of field keeping focus on her face while the background gently blurs, enhancing the cinematic quality.
[!] txt2img mode
  0%|          | 0/47 [00:00<?, ?it/s]
  2%|▏         | 1/47 [00:01<00:49,  1.08s/it]
  4%|▍         | 2/47 [00:02<00:44,  1.01it/s]
  6%|▋         | 3/47 [00:03<00:45,  1.03s/it]
  9%|▊         | 4/47 [00:04<00:44,  1.05s/it]
 11%|█         | 5/47 [00:05<00:44,  1.06s/it]
 13%|█▎        | 6/47 [00:06<00:43,  1.07s/it]
 15%|█▍        | 7/47 [00:07<00:42,  1.07s/it]
 17%|█▋        | 8/47 [00:08<00:41,  1.07s/it]
 19%|█▉        | 9/47 [00:09<00:40,  1.08s/it]
 21%|██▏       | 10/47 [00:10<00:39,  1.08s/it]
 23%|██▎       | 11/47 [00:11<00:38,  1.08s/it]
 26%|██▌       | 12/47 [00:12<00:37,  1.08s/it]
 28%|██▊       | 13/47 [00:13<00:36,  1.08s/it]
 30%|██▉       | 14/47 [00:14<00:35,  1.08s/it]
 32%|███▏      | 15/47 [00:16<00:34,  1.08s/it]
 34%|███▍      | 16/47 [00:17<00:33,  1.08s/it]
 36%|███▌      | 17/47 [00:18<00:32,  1.08s/it]
 38%|███▊      | 18/47 [00:19<00:31,  1.08s/it]
 40%|████      | 19/47 [00:20<00:30,  1.08s/it]
 43%|████▎     | 20/47 [00:21<00:29,  1.08s/it]
 45%|████▍     | 21/47 [00:22<00:28,  1.08s/it]
 47%|████▋     | 22/47 [00:23<00:27,  1.08s/it]
 49%|████▉     | 23/47 [00:24<00:25,  1.08s/it]
 51%|█████     | 24/47 [00:25<00:24,  1.08s/it]
 53%|█████▎    | 25/47 [00:26<00:23,  1.08s/it]
 55%|█████▌    | 26/47 [00:27<00:22,  1.08s/it]
 57%|█████▋    | 27/47 [00:28<00:21,  1.08s/it]
 60%|█████▉    | 28/47 [00:30<00:20,  1.08s/it]
 62%|██████▏   | 29/47 [00:31<00:19,  1.08s/it]
 64%|██████▍   | 30/47 [00:32<00:18,  1.08s/it]
 66%|██████▌   | 31/47 [00:33<00:17,  1.08s/it]
 68%|██████▊   | 32/47 [00:34<00:16,  1.08s/it]
 70%|███████   | 33/47 [00:35<00:15,  1.08s/it]
 72%|███████▏  | 34/47 [00:36<00:14,  1.08s/it]
 74%|███████▍  | 35/47 [00:37<00:12,  1.08s/it]
 77%|███████▋  | 36/47 [00:38<00:11,  1.08s/it]
 79%|███████▊  | 37/47 [00:39<00:10,  1.08s/it]
 81%|████████  | 38/47 [00:40<00:09,  1.08s/it]
 83%|████████▎ | 39/47 [00:41<00:08,  1.08s/it]
 85%|████████▌ | 40/47 [00:43<00:07,  1.08s/it]
 87%|████████▋ | 41/47 [00:44<00:06,  1.08s/it]
 89%|████████▉ | 42/47 [00:45<00:05,  1.08s/it]
 91%|█████████▏| 43/47 [00:46<00:04,  1.08s/it]
 94%|█████████▎| 44/47 [00:47<00:03,  1.08s/it]
 96%|█████████▌| 45/47 [00:48<00:02,  1.08s/it]
 98%|█████████▊| 46/47 [00:49<00:01,  1.08s/it]
100%|██████████| 47/47 [00:50<00:00,  1.08s/it]
100%|██████████| 47/47 [00:50<00:00,  1.08s/it]
Total safe images: 4 out of 4
Version Details
Version ID
2a01d27ead8a0d857a1f985ab225eb1732d0bdc3783625e628cc7dccb5835863
Version Created
July 28, 2025
Run on Replicate →