biggpt1/osdress-one 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
ALTSB it white A beautiful woman ALTSB in a traditional Ossetian white dress TOK, standing gracefully in a serene outdoor setting. The dress is intricately embroidered with delicate silver patterns, flowing elegantly around her as a gentle breeze lifts its edges. She wears a matching white headscarf adorned with subtle lace, framing her striking features—high cheekbones, deep brown eyes, and a poised expression. Her long, dark hair cascades beneath the scarf, partially visible.
The setting is a picturesque Ossetian mountain landscape bathed in soft, golden sunlight, with lush green meadows and distant snow-capped peaks in the background. The scene is captured in the style of a vintage Kodak film photograph, evoking a warm, nostalgic atmosphere with rich yet slightly muted tones. Light leaks and a soft grain texture add to the authenticity of the film aesthetic.
Her pose is elegant yet natural, with her hands gently clasped in front of her. A sense of quiet dignity and cultural pride emanates from her stance, as the folds of her traditional dress catch the light, revealing intricate embroidery. The shallow depth of field emphasizes her as the central focus, while the blurred background enhances the dreamlike quality of the image. The overall composition blends timeless elegance with a cinematic, old-film charm.
"Output
Performance Metrics
34.58s
Prediction Time
34.60s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "ALTSB it white A beautiful woman ALTSB in a traditional Ossetian white dress TOK, standing gracefully in a serene outdoor setting. The dress is intricately embroidered with delicate silver patterns, flowing elegantly around her as a gentle breeze lifts its edges. She wears a matching white headscarf adorned with subtle lace, framing her striking features—high cheekbones, deep brown eyes, and a poised expression. Her long, dark hair cascades beneath the scarf, partially visible.\n\nThe setting is a picturesque Ossetian mountain landscape bathed in soft, golden sunlight, with lush green meadows and distant snow-capped peaks in the background. The scene is captured in the style of a vintage Kodak film photograph, evoking a warm, nostalgic atmosphere with rich yet slightly muted tones. Light leaks and a soft grain texture add to the authenticity of the film aesthetic.\n\nHer pose is elegant yet natural, with her hands gently clasped in front of her. A sense of quiet dignity and cultural pride emanates from her stance, as the folds of her traditional dress catch the light, revealing intricate embroidery. The shallow depth of field emphasizes her as the central focus, while the blurred background enhances the dreamlike quality of the image. The overall composition blends timeless elegance with a cinematic, old-film charm.",
"go_fast": false,
"extra_lora": "biguloff/alina-tseba",
"lora_scale": 0.88,
"megapixels": "1",
"num_outputs": 3,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 0.79,
"num_inference_steps": 28
}
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- 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
- 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
- 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)
- 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
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- 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
- 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
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- 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
- 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
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- 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
- 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
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
free=28863928610816 Downloading weights 2025-02-05T21:10:47Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpjvrh9_4m/weights url=https://replicate.delivery/xezq/Qssp4kEFTiKNL5UWfH5U2R9YcuEp3Uhz4Ssgfqj4QBkDMVMUA/trained_model.tar 2025-02-05T21:10:50Z | INFO | [ Complete ] dest=/tmp/tmpjvrh9_4m/weights size="355 MB" total_elapsed=2.473s url=https://replicate.delivery/xezq/Qssp4kEFTiKNL5UWfH5U2R9YcuEp3Uhz4Ssgfqj4QBkDMVMUA/trained_model.tar Downloaded weights in 2.50s free=28863572684800 Downloading weights 2025-02-05T21:10:50Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp4h1944ms/weights url=https://replicate.com/biguloff/alina-tseba/_weights 2025-02-05T21:10:51Z | INFO | [ Redirect ] redirect_url=https://replicate.delivery/yhqm/X9bP4Eu4u1YBOBQVEQ5mbfcUvADnLvuFojFD1S3krgmoUP1JA/trained_model.tar url=https://replicate.com/biguloff/alina-tseba/_weights 2025-02-05T21:10:57Z | INFO | [ Complete ] dest=/tmp/tmp4h1944ms/weights size="344 MB" total_elapsed=6.732s url=https://replicate.com/biguloff/alina-tseba/_weights Downloaded weights in 6.76s Loaded LoRAs in 10.72s Using seed: 19742 Prompt: ALTSB it white A beautiful woman ALTSB in a traditional Ossetian white dress TOK, standing gracefully in a serene outdoor setting. The dress is intricately embroidered with delicate silver patterns, flowing elegantly around her as a gentle breeze lifts its edges. She wears a matching white headscarf adorned with subtle lace, framing her striking features—high cheekbones, deep brown eyes, and a poised expression. Her long, dark hair cascades beneath the scarf, partially visible. The setting is a picturesque Ossetian mountain landscape bathed in soft, golden sunlight, with lush green meadows and distant snow-capped peaks in the background. The scene is captured in the style of a vintage Kodak film photograph, evoking a warm, nostalgic atmosphere with rich yet slightly muted tones. Light leaks and a soft grain texture add to the authenticity of the film aesthetic. Her pose is elegant yet natural, with her hands gently clasped in front of her. A sense of quiet dignity and cultural pride emanates from her stance, as the folds of her traditional dress catch the light, revealing intricate embroidery. The shallow depth of field emphasizes her as the central focus, while the blurred background enhances the dreamlike quality of the image. The overall composition blends timeless elegance with a cinematic, old-film charm. [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:22, 1.21it/s] 7%|▋ | 2/28 [00:01<00:19, 1.32it/s] 11%|█ | 3/28 [00:02<00:19, 1.26it/s] 14%|█▍ | 4/28 [00:03<00:19, 1.24it/s] 18%|█▊ | 5/28 [00:04<00:18, 1.23it/s] 21%|██▏ | 6/28 [00:04<00:18, 1.22it/s] 25%|██▌ | 7/28 [00:05<00:17, 1.22it/s] 29%|██▊ | 8/28 [00:06<00:16, 1.21it/s] 32%|███▏ | 9/28 [00:07<00:15, 1.21it/s] 36%|███▌ | 10/28 [00:08<00:14, 1.21it/s] 39%|███▉ | 11/28 [00:09<00:14, 1.21it/s] 43%|████▎ | 12/28 [00:09<00:13, 1.21it/s] 46%|████▋ | 13/28 [00:10<00:12, 1.21it/s] 50%|█████ | 14/28 [00:11<00:11, 1.20it/s] 54%|█████▎ | 15/28 [00:12<00:10, 1.20it/s] 57%|█████▋ | 16/28 [00:13<00:09, 1.20it/s] 61%|██████ | 17/28 [00:13<00:09, 1.20it/s] 64%|██████▍ | 18/28 [00:14<00:08, 1.21it/s] 68%|██████▊ | 19/28 [00:15<00:07, 1.20it/s] 71%|███████▏ | 20/28 [00:16<00:06, 1.21it/s] 75%|███████▌ | 21/28 [00:17<00:05, 1.21it/s] 79%|███████▊ | 22/28 [00:18<00:04, 1.21it/s] 82%|████████▏ | 23/28 [00:18<00:04, 1.20it/s] 86%|████████▌ | 24/28 [00:19<00:03, 1.20it/s] 89%|████████▉ | 25/28 [00:20<00:02, 1.21it/s] 93%|█████████▎| 26/28 [00:21<00:01, 1.20it/s] 96%|█████████▋| 27/28 [00:22<00:00, 1.20it/s] 100%|██████████| 28/28 [00:23<00:00, 1.20it/s] 100%|██████████| 28/28 [00:23<00:00, 1.21it/s] Total safe images: 3 out of 3
Version Details
- Version ID
30ecc43fece87d3f7171e18e80a38242f7a00f12393c7d062d976052c2bcc6b3- Version Created
- February 5, 2025