biggpt1/pana-video 🖼️🔢❓📝✓ → 🖼️

▶️ 75 runs 📅 Feb 2025 ⚙️ Cog 0.13.7
image-inpainting image-to-image lora lora-person text-to-image

About

Example Output

Prompt:

"

Ultra-realistic photo of a couple, PNA_men on the left in red clothes and PNA_woman on the right, inside a vintage tram, surrounded by an explosion of lush flowers. On the left, PNA_men wears a deep crimson-red zip-up tracksuit with white piping details over a plain white t-shirt. He holds a small metallic coffee cup in his hand. On the right, PNA_woman, with voluminous curly red hair, wears a navy-blue tracksuit jacket with a small embroidered logo, a loose white t-shirt, and matching navy-blue trousers. Her nails are painted in a mix of bold yellow and deep red, and she wears multiple rings.

The tram’s interior is filled with a riot of colors, as flowers in pink, red, blue, purple, and white burst from every surface—walls, ceiling, seats, and floor. Roses, peonies, hydrangeas, carnations, and lilacs cascade from hanging baskets, climb polished brass handrails, and spill across windowsills. Some petals appear almost neon, glowing under the warm sunlight streaming through the windows, casting colorful reflections onto the couple’s faces.

They share a lively moment, the woman laughing with her head tilted back while the man gazes at her with a soft smile. The background blurs with motion outside the tram, showing streaks of city life in pastel blues, soft oranges, and golden yellows, emphasizing movement. The foreground keeps sharp detail, highlighting the dewdrops on flower petals and the fabric textures of their clothing.

The atmosphere is dreamlike yet vivid, a mix of nostalgic romance and urban energy, with saturated colors, soft natural light, and a gentle interplay of textures from flowers, fabric, and reflections.

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

45.12s Prediction Time
45.29s Total Time
All Input Parameters 
{
  "model": "dev",
  "prompt": "Ultra-realistic photo of a couple, PNA_men on the left in red clothes and PNA_woman on the right, inside a vintage tram, surrounded by an explosion of lush flowers. On the left, PNA_men wears a deep crimson-red zip-up tracksuit with white piping details over a plain white t-shirt. He holds a small metallic coffee cup in his hand. On the right, PNA_woman, with voluminous curly red hair, wears a navy-blue tracksuit jacket with a small embroidered logo, a loose white t-shirt, and matching navy-blue trousers. Her nails are painted in a mix of bold yellow and deep red, and she wears multiple rings.\n\nThe tram’s interior is filled with a riot of colors, as flowers in pink, red, blue, purple, and white burst from every surface—walls, ceiling, seats, and floor. Roses, peonies, hydrangeas, carnations, and lilacs cascade from hanging baskets, climb polished brass handrails, and spill across windowsills. Some petals appear almost neon, glowing under the warm sunlight streaming through the windows, casting colorful reflections onto the couple’s faces.\n\nThey share a lively moment, the woman laughing with her head tilted back while the man gazes at her with a soft smile. The background blurs with motion outside the tram, showing streaks of city life in pastel blues, soft oranges, and golden yellows, emphasizing movement. The foreground keeps sharp detail, highlighting the dewdrops on flower petals and the fabric textures of their clothing.\n\nThe atmosphere is dreamlike yet vivid, a mix of nostalgic romance and urban energy, with saturated colors, soft natural light, and a gentle interplay of textures from flowers, fabric, and reflections.",
  "go_fast": false,
  "extra_lora": "https://civitai.com/api/download/models/1273564?type=Model&format=SafeTensor&token=ae82acec6ad7050b7f1e3654da2bb265",
  "lora_scale": 0.82,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 2.5,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 0.68,
  "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=27806258122752
Downloading weights
2025-02-13T16:56:33Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpt1vuo5u5/weights url=https://replicate.delivery/xezq/fHjDtjTZ692DdK487muGQgxjX0tWc7psKmVjaeZMSbPdq6OUA/trained_model.tar
2025-02-13T16:56:38Z | INFO  | [ Complete ] dest=/tmp/tmpt1vuo5u5/weights size="355 MB" total_elapsed=4.949s url=https://replicate.delivery/xezq/fHjDtjTZ692DdK487muGQgxjX0tWc7psKmVjaeZMSbPdq6OUA/trained_model.tar
Downloaded weights in 4.98s
free=27805901287424
Downloading weights
2025-02-13T16:56:38Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/2546d3e98d5430a5 url=https://civitai.com/api/download/models/1273564?type=Model&format=SafeTensor&token=ae82acec6ad7050b7f1e3654da2bb265
2025-02-13T16:56:39Z | INFO  | [ Redirect ] redirect_url=https://civitai-delivery-worker-prod.5ac0637cfd0766c97916cefa3764fbdf.r2.cloudflarestorage.com/model/5019728/flower512DevF1K.IGzb.safetensors?X-Amz-Expires=86400&response-content-disposition=attachment%3B%20filename%3D%22flower_512_dev_f1_k.safetensors%22&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=e01358d793ad6966166af8b3064953ad/20250213/us-east-1/s3/aws4_request&X-Amz-Date=20250213T165639Z&X-Amz-SignedHeaders=host&X-Amz-Signature=2daf354b98e79cfa000f21598ff3b7005fd43e9eb38097466dacb3f62bdd5926 url=https://civitai.com/api/download/models/1273564?type=Model&format=SafeTensor&token=ae82acec6ad7050b7f1e3654da2bb265
2025-02-13T16:56:44Z | INFO  | [ Complete ] dest=/src/weights-cache/2546d3e98d5430a5 size="159 MB" total_elapsed=5.810s url=https://civitai.com/api/download/models/1273564?type=Model&format=SafeTensor&token=ae82acec6ad7050b7f1e3654da2bb265
Downloaded weights in 5.83s
Loaded LoRAs in 12.18s
Using seed: 61131
Prompt: Ultra-realistic photo of a couple, PNA_men on the left in red clothes and PNA_woman on the right, inside a vintage tram, surrounded by an explosion of lush flowers. On the left, PNA_men wears a deep crimson-red zip-up tracksuit with white piping details over a plain white t-shirt. He holds a small metallic coffee cup in his hand. On the right, PNA_woman, with voluminous curly red hair, wears a navy-blue tracksuit jacket with a small embroidered logo, a loose white t-shirt, and matching navy-blue trousers. Her nails are painted in a mix of bold yellow and deep red, and she wears multiple rings.
The tram’s interior is filled with a riot of colors, as flowers in pink, red, blue, purple, and white burst from every surface—walls, ceiling, seats, and floor. Roses, peonies, hydrangeas, carnations, and lilacs cascade from hanging baskets, climb polished brass handrails, and spill across windowsills. Some petals appear almost neon, glowing under the warm sunlight streaming through the windows, casting colorful reflections onto the couple’s faces.
They share a lively moment, the woman laughing with her head tilted back while the man gazes at her with a soft smile. The background blurs with motion outside the tram, showing streaks of city life in pastel blues, soft oranges, and golden yellows, emphasizing movement. The foreground keeps sharp detail, highlighting the dewdrops on flower petals and the fabric textures of their clothing.
The atmosphere is dreamlike yet vivid, a mix of nostalgic romance and urban energy, with saturated colors, soft natural light, and a gentle interplay of textures from flowers, fabric, and reflections.
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:01<00:29,  1.10s/it]
  7%|▋         | 2/28 [00:02<00:26,  1.01s/it]
 11%|█         | 3/28 [00:03<00:26,  1.05s/it]
 14%|█▍        | 4/28 [00:04<00:25,  1.07s/it]
 18%|█▊        | 5/28 [00:05<00:24,  1.08s/it]
 21%|██▏       | 6/28 [00:06<00:23,  1.09s/it]
 25%|██▌       | 7/28 [00:07<00:23,  1.10s/it]
 29%|██▊       | 8/28 [00:08<00:21,  1.10s/it]
 32%|███▏      | 9/28 [00:09<00:20,  1.10s/it]
 36%|███▌      | 10/28 [00:10<00:19,  1.10s/it]
 39%|███▉      | 11/28 [00:11<00:18,  1.10s/it]
 43%|████▎     | 12/28 [00:13<00:17,  1.10s/it]
 46%|████▋     | 13/28 [00:14<00:16,  1.10s/it]
 50%|█████     | 14/28 [00:15<00:15,  1.10s/it]
 54%|█████▎    | 15/28 [00:16<00:14,  1.10s/it]
 57%|█████▋    | 16/28 [00:17<00:13,  1.11s/it]
 61%|██████    | 17/28 [00:18<00:12,  1.11s/it]
 64%|██████▍   | 18/28 [00:19<00:11,  1.11s/it]
 68%|██████▊   | 19/28 [00:20<00:09,  1.11s/it]
 71%|███████▏  | 20/28 [00:21<00:08,  1.11s/it]
 75%|███████▌  | 21/28 [00:23<00:07,  1.11s/it]
 79%|███████▊  | 22/28 [00:24<00:06,  1.11s/it]
 82%|████████▏ | 23/28 [00:25<00:05,  1.11s/it]
 86%|████████▌ | 24/28 [00:26<00:04,  1.11s/it]
 89%|████████▉ | 25/28 [00:27<00:03,  1.11s/it]
 93%|█████████▎| 26/28 [00:28<00:02,  1.11s/it]
 96%|█████████▋| 27/28 [00:29<00:01,  1.11s/it]
100%|██████████| 28/28 [00:30<00:00,  1.11s/it]
100%|██████████| 28/28 [00:30<00:00,  1.10s/it]
Total safe images: 4 out of 4
Version Details
Version ID
62a7ca417bd135fdb3468769ec98b8a6042fba49b71999f27cd70f1b7a5abfde
Version Created
February 13, 2025
Run on Replicate →