biggpt1/regina 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
Professional photoshoot of an RGN subject in classic 1960s glamour style, inspired by vintage Playboy covers. The subject is posed gracefully on an ornate, golden velvet chaise lounge, evoking old-Hollywood elegance. She wears a form-fitting strapless black cocktail dress with lace side panels and a sweetheart neckline that accentuates the hourglass silhouette. Her legs are crossed casually yet confidently, one arm draped elegantly over the armrest, the other resting lightly on her thigh.
Her blonde, shoulder-length hair is styled in voluminous retro curls, parted to the side, with soft waves framing her face. Her makeup features bold red lipstick, black winged eyeliner, and flawless matte skin — a true nod to 1962 glamour.
The scene is softly lit with warm studio lighting, simulating a classic film grain texture. The background features vintage wallpaper in gold tones and subtle vignetting around the edges, adding depth and nostalgic character.
Rendered in a cinematic editorial tone, shot on a Canon R5 with an 85mm prime lens, using soft diffusion filters to mimic the magazine cover aesthetics of the 60s. The image is styled as a retro magazine cover layout, with subtle paper texture and authentic typography.
"Output
Performance Metrics
34.43s
Prediction Time
34.59s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Professional photoshoot of an RGN subject in classic 1960s glamour style, inspired by vintage Playboy covers. The subject is posed gracefully on an ornate, golden velvet chaise lounge, evoking old-Hollywood elegance. She wears a form-fitting strapless black cocktail dress with lace side panels and a sweetheart neckline that accentuates the hourglass silhouette. Her legs are crossed casually yet confidently, one arm draped elegantly over the armrest, the other resting lightly on her thigh.\n\nHer blonde, shoulder-length hair is styled in voluminous retro curls, parted to the side, with soft waves framing her face. Her makeup features bold red lipstick, black winged eyeliner, and flawless matte skin — a true nod to 1962 glamour.\n\nThe scene is softly lit with warm studio lighting, simulating a classic film grain texture. The background features vintage wallpaper in gold tones and subtle vignetting around the edges, adding depth and nostalgic character.\n\nRendered in a cinematic editorial tone, shot on a Canon R5 with an 85mm prime lens, using soft diffusion filters to mimic the magazine cover aesthetics of the 60s. The image is styled as a retro magazine cover layout, with subtle paper texture and authentic typography.",
"go_fast": false,
"lora_scale": 0.89,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "1:1",
"output_format": "png",
"guidance_scale": 3.46,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"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=27438377799680 Downloading weights 2025-05-22T23:53:50Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpmge998el/weights url=https://replicate.delivery/xezq/iMfOiq7dLP38Ea8hPltgTjruUxYiMqjHfWqwxVtdgzdAoWvUA/trained_model.tar 2025-05-22T23:53:50Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-05-22T23:53:53Z | INFO | [ Complete ] dest=/tmp/tmpmge998el/weights size="355 MB" total_elapsed=2.378s url=https://replicate.delivery/xezq/iMfOiq7dLP38Ea8hPltgTjruUxYiMqjHfWqwxVtdgzdAoWvUA/trained_model.tar Downloaded weights in 2.41s Loaded LoRAs in 3.02s Using seed: 5 Prompt: Professional photoshoot of an RGN subject in classic 1960s glamour style, inspired by vintage Playboy covers. The subject is posed gracefully on an ornate, golden velvet chaise lounge, evoking old-Hollywood elegance. She wears a form-fitting strapless black cocktail dress with lace side panels and a sweetheart neckline that accentuates the hourglass silhouette. Her legs are crossed casually yet confidently, one arm draped elegantly over the armrest, the other resting lightly on her thigh. Her blonde, shoulder-length hair is styled in voluminous retro curls, parted to the side, with soft waves framing her face. Her makeup features bold red lipstick, black winged eyeliner, and flawless matte skin — a true nod to 1962 glamour. The scene is softly lit with warm studio lighting, simulating a classic film grain texture. The background features vintage wallpaper in gold tones and subtle vignetting around the edges, adding depth and nostalgic character. Rendered in a cinematic editorial tone, shot on a Canon R5 with an 85mm prime lens, using soft diffusion filters to mimic the magazine cover aesthetics of the 60s. The image is styled as a retro magazine cover layout, with subtle paper texture and authentic typography. [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:28, 1.05s/it] 7%|▋ | 2/28 [00:01<00:24, 1.08it/s] 11%|█ | 3/28 [00:02<00:24, 1.02it/s] 14%|█▍ | 4/28 [00:03<00:24, 1.00s/it] 18%|█▊ | 5/28 [00:05<00:23, 1.02s/it] 21%|██▏ | 6/28 [00:06<00:22, 1.03s/it] 25%|██▌ | 7/28 [00:07<00:21, 1.03s/it] 29%|██▊ | 8/28 [00:08<00:20, 1.04s/it] 32%|███▏ | 9/28 [00:09<00:19, 1.04s/it] 36%|███▌ | 10/28 [00:10<00:18, 1.04s/it] 39%|███▉ | 11/28 [00:11<00:17, 1.04s/it] 43%|████▎ | 12/28 [00:12<00:16, 1.04s/it] 46%|████▋ | 13/28 [00:13<00:15, 1.04s/it] 50%|█████ | 14/28 [00:14<00:14, 1.05s/it] 54%|█████▎ | 15/28 [00:15<00:13, 1.04s/it] 57%|█████▋ | 16/28 [00:16<00:12, 1.04s/it] 61%|██████ | 17/28 [00:17<00:11, 1.04s/it] 64%|██████▍ | 18/28 [00:18<00:10, 1.05s/it] 68%|██████▊ | 19/28 [00:19<00:09, 1.05s/it] 71%|███████▏ | 20/28 [00:20<00:08, 1.05s/it] 75%|███████▌ | 21/28 [00:21<00:07, 1.05s/it] 79%|███████▊ | 22/28 [00:22<00:06, 1.05s/it] 82%|████████▏ | 23/28 [00:23<00:05, 1.05s/it] 86%|████████▌ | 24/28 [00:24<00:04, 1.05s/it] 89%|████████▉ | 25/28 [00:25<00:03, 1.05s/it] 93%|█████████▎| 26/28 [00:26<00:02, 1.05s/it] 96%|█████████▋| 27/28 [00:28<00:01, 1.05s/it] 100%|██████████| 28/28 [00:29<00:00, 1.05s/it] 100%|██████████| 28/28 [00:29<00:00, 1.04s/it] Total safe images: 4 out of 4
Version Details
- Version ID
bc459575f5c76e3e727de02b77db8ed3b8e03ce01031a965cfabbf0be265d94c- Version Created
- May 22, 2025