ia01/ishaan-flux 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"Generate the image of smart 23 year old ISH. He is seen standing on a beach in black shorts, and a lose floral blue shirt with his top two buttons unbuttoned. He is wearing a black cap and since the sun is bright he is also wearing sunglasses/shades. He is standing barefoot on the sand. We can see he is well built. The waves should be flowing behind him and it should be an image with the highest quality of realism. ISH should carry a subtle seductive smile. His entire body and outfit should be visible. he should also be seen wearing a few rugged black bracelets on one wrist."
Output
Performance Metrics
13.62s
Prediction Time
97.93s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Generate the image of smart 23 year old ISH. He is seen standing on a beach in black shorts, and a lose floral blue shirt with his top two buttons unbuttoned. He is wearing a black cap and since the sun is bright he is also wearing sunglasses/shades. He is standing barefoot on the sand. We can see he is well built. The waves should be flowing behind him and it should be an image with the highest quality of realism. ISH should carry a subtle seductive smile. His entire body and outfit should be visible. he should also be seen wearing a few rugged black bracelets on one wrist.",
"lora_scale": 1,
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "jpg",
"guidance_scale": 2.71,
"output_quality": 90,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 32
}
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: 64288 Prompt: Generate the image of smart 23 year old ISH. He is seen standing on a beach in black shorts, and a lose floral blue shirt with his top two buttons unbuttoned. He is wearing a black cap and since the sun is bright he is also wearing sunglasses/shades. He is standing barefoot on the sand. We can see he is well built. The waves should be flowing behind him and it should be an image with the highest quality of realism. ISH should carry a subtle seductive smile. His entire body and outfit should be visible. he should also be seen wearing a few rugged black bracelets on one wrist. [!] txt2img mode Using dev model free=9336197808128 Downloading weights 2024-10-04T23:21:00Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpn7a_0v46/weights url=https://replicate.delivery/yhqm/aNo0SHEHVd7NDJHixcPUfWqcdlOw9x8Y1LFpIymfAtffI4NOB/trained_model.tar 2024-10-04T23:21:02Z | INFO | [ Complete ] dest=/tmp/tmpn7a_0v46/weights size="215 MB" total_elapsed=1.516s url=https://replicate.delivery/yhqm/aNo0SHEHVd7NDJHixcPUfWqcdlOw9x8Y1LFpIymfAtffI4NOB/trained_model.tar Downloaded weights in 1.55s Loaded LoRAs in 2.27s 0%| | 0/32 [00:00<?, ?it/s] 3%|▎ | 1/32 [00:00<00:10, 2.86it/s] 6%|▋ | 2/32 [00:00<00:09, 3.19it/s] 9%|▉ | 3/32 [00:00<00:09, 3.04it/s] 12%|█▎ | 4/32 [00:01<00:09, 2.97it/s] 16%|█▌ | 5/32 [00:01<00:09, 2.93it/s] 19%|█▉ | 6/32 [00:02<00:08, 2.90it/s] 22%|██▏ | 7/32 [00:02<00:08, 2.89it/s] 25%|██▌ | 8/32 [00:02<00:08, 2.88it/s] 28%|██▊ | 9/32 [00:03<00:07, 2.88it/s] 31%|███▏ | 10/32 [00:03<00:07, 2.87it/s] 34%|███▍ | 11/32 [00:03<00:07, 2.87it/s] 38%|███▊ | 12/32 [00:04<00:06, 2.87it/s] 41%|████ | 13/32 [00:04<00:06, 2.87it/s] 44%|████▍ | 14/32 [00:04<00:06, 2.87it/s] 47%|████▋ | 15/32 [00:05<00:05, 2.87it/s] 50%|█████ | 16/32 [00:05<00:05, 2.87it/s] 53%|█████▎ | 17/32 [00:05<00:05, 2.87it/s] 56%|█████▋ | 18/32 [00:06<00:04, 2.87it/s] 59%|█████▉ | 19/32 [00:06<00:04, 2.87it/s] 62%|██████▎ | 20/32 [00:06<00:04, 2.87it/s] 66%|██████▌ | 21/32 [00:07<00:03, 2.87it/s] 69%|██████▉ | 22/32 [00:07<00:03, 2.87it/s] 72%|███████▏ | 23/32 [00:07<00:03, 2.87it/s] 75%|███████▌ | 24/32 [00:08<00:02, 2.87it/s] 78%|███████▊ | 25/32 [00:08<00:02, 2.87it/s] 81%|████████▏ | 26/32 [00:09<00:02, 2.87it/s] 84%|████████▍ | 27/32 [00:09<00:01, 2.87it/s] 88%|████████▊ | 28/32 [00:09<00:01, 2.87it/s] 91%|█████████ | 29/32 [00:10<00:01, 2.87it/s] 94%|█████████▍| 30/32 [00:10<00:00, 2.87it/s] 97%|█████████▋| 31/32 [00:10<00:00, 2.87it/s] 100%|██████████| 32/32 [00:11<00:00, 2.87it/s] 100%|██████████| 32/32 [00:11<00:00, 2.88it/s]
Version Details
- Version ID
f31414cf367adee5211d3e17dca5cdb7f25458b76d9a272dfda8cac06d6852ba- Version Created
- October 4, 2024