karlvann/pauline_close 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"A photo of a model with long blonde hair and a pink onesie sitting on a a model on a grey mattress with black sides..the onesie has white around the cuffs. The room is nature themed and evokes a sense of spaciousness. The model's skin tone should contrast warmly with the pajamas, suggesting a tanned complexion. The model has a relaxed pose. It's in a room with warm orange toned walls , with a large window revealing a balcony and beach scene, with tall plants, The model wears a pastel apricot pajama and she looks like shes glowing with happiness. Light the scene with warm, diffused lighting, intimate atmosphere. The overall color palette should be dominated by warm tones - peaches, creams, and soft golds. Heavy film grain effect "
Output
Performance Metrics
42.68s
Prediction Time
42.69s
Total Time
All Input Parameters
{
"seed": 60238,
"model": "dev",
"prompt": "A photo of a model with long blonde hair and a pink onesie sitting on a a model on a grey mattress with black sides..the onesie has white around the cuffs. The room is nature themed and evokes a sense of spaciousness. The model's skin tone should contrast warmly with the pajamas, suggesting a tanned complexion. The model has a relaxed pose. It's in a room with warm orange toned walls , with a large window revealing a balcony and beach scene, with tall plants, The model wears a pastel apricot pajama and she looks like shes glowing with happiness. Light the scene with warm, diffused lighting, intimate atmosphere. The overall color palette should be dominated by warm tones - peaches, creams, and soft golds. Heavy film grain effect ",
"extra_lora": "karlvann/earth38",
"lora_scale": 1,
"num_outputs": 4,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3.5,
"output_quality": 90,
"prompt_strength": 0.8,
"extra_lora_scale": 0.1,
"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
Using seed: 60238 Prompt: A photo of a model with long blonde hair and a pink onesie sitting on a a model on a grey mattress with black sides..the onesie has white around the cuffs. The room is nature themed and evokes a sense of spaciousness. The model's skin tone should contrast warmly with the pajamas, suggesting a tanned complexion. The model has a relaxed pose. It's in a room with warm orange toned walls , with a large window revealing a balcony and beach scene, with tall plants, The model wears a pastel apricot pajama and she looks like shes glowing with happiness. Light the scene with warm, diffused lighting, intimate atmosphere. The overall color palette should be dominated by warm tones - peaches, creams, and soft golds. Heavy film grain effect [!] txt2img mode Using dev model Loading extra LoRA weights from: karlvann/earth38 Weights already loaded Loaded LoRAs in 0.06s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:40, 1.49s/it] 7%|▋ | 2/28 [00:02<00:35, 1.37s/it] 11%|█ | 3/28 [00:04<00:35, 1.42s/it] 14%|█▍ | 4/28 [00:05<00:34, 1.45s/it] 18%|█▊ | 5/28 [00:07<00:33, 1.46s/it] 21%|██▏ | 6/28 [00:08<00:32, 1.47s/it] 25%|██▌ | 7/28 [00:10<00:30, 1.47s/it] 29%|██▊ | 8/28 [00:11<00:29, 1.48s/it] 32%|███▏ | 9/28 [00:13<00:28, 1.48s/it] 36%|███▌ | 10/28 [00:14<00:26, 1.48s/it] 39%|███▉ | 11/28 [00:16<00:25, 1.48s/it] 43%|████▎ | 12/28 [00:17<00:23, 1.48s/it] 46%|████▋ | 13/28 [00:19<00:22, 1.48s/it] 50%|█████ | 14/28 [00:20<00:20, 1.48s/it] 54%|█████▎ | 15/28 [00:22<00:19, 1.48s/it] 57%|█████▋ | 16/28 [00:23<00:17, 1.48s/it] 61%|██████ | 17/28 [00:25<00:16, 1.48s/it] 64%|██████▍ | 18/28 [00:26<00:14, 1.48s/it] 68%|██████▊ | 19/28 [00:28<00:13, 1.48s/it] 71%|███████▏ | 20/28 [00:29<00:11, 1.48s/it] 75%|███████▌ | 21/28 [00:30<00:10, 1.49s/it] 79%|███████▊ | 22/28 [00:32<00:08, 1.49s/it] 82%|████████▏ | 23/28 [00:33<00:07, 1.49s/it] 86%|████████▌ | 24/28 [00:35<00:05, 1.49s/it] 89%|████████▉ | 25/28 [00:36<00:04, 1.49s/it] 93%|█████████▎| 26/28 [00:38<00:02, 1.49s/it] 96%|█████████▋| 27/28 [00:39<00:01, 1.49s/it] 100%|██████████| 28/28 [00:41<00:00, 1.49s/it] 100%|██████████| 28/28 [00:41<00:00, 1.48s/it]
Version Details
- Version ID
470a9426203fc1c43b0569a4242c1865958f6dddc6c6cbbb0657da0549d73eb9- Version Created
- November 4, 2024