tungsten-logo
Sign In
miamodel-sdxl
miamodel-sdxl

miamodel-sdxl

16 stars
Version: v3.0
Input
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
Output
https://files.tungsten.run/uploads/d958950f2ed2421db6f38ed18f000924/00000-240075782.webp
https://files.tungsten.run/uploads/2237f646209542aeba5760dcefb1ebe9/00001-240075783.webp
https://files.tungsten.run/uploads/882eb5a3175647409be9e5287edae34f/00002-240075784.webp
This example was created by sparks
Finished in 104.8 seconds
Setting up the model... Preparing inputs... Processing... Using seed 240075782 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: fashion photography of topless white elven girl, Cara Delevingne, with medium breasts, with short ears, pink nipples, perky nipples, in a forest, symmetrical, octane render, 35mm, bokeh, 9:16, (intricate details:1.12), hdr, (intricate details, hyperdetailed:1.15), (natural skin texture, hyperrealism, soft light, sharp:1.2), look at the camera, demure, <lora:add-detail-xl:1.5> Full negative prompt: (worst quality:2, low quality:2), (deformed, distorted, disfigured), (bad eyes, wrong lips, weird mouth, bad teeth, mutated hands and fingers:1.2), (bad anatomy), wrong anatomy, amputation, extra limb, missing limb, floating limbs, disconnected limbs, mutation, ugly, disgusting, (signature, watermark, username, blurry, artist name), asian 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:28, 3.05s/it] 7%|▋ | 2/30 [00:05<01:08, 2.45s/it] 10%|█ | 3/30 [00:07<01:01, 2.26s/it] 13%|█▎ | 4/30 [00:09<00:56, 2.18s/it] 17%|█▋ | 5/30 [00:11<00:53, 2.13s/it] 20%|██ | 6/30 [00:13<00:50, 2.11s/it] 23%|██▎ | 7/30 [00:15<00:48, 2.09s/it] 27%|██▋ | 8/30 [00:17<00:45, 2.08s/it] 30%|███ | 9/30 [00:19<00:43, 2.07s/it] 33%|███▎ | 10/30 [00:21<00:41, 2.07s/it] 37%|███▋ | 11/30 [00:23<00:39, 2.07s/it] 40%|████ | 12/30 [00:25<00:37, 2.06s/it] 43%|████▎ | 13/30 [00:27<00:35, 2.06s/it] 47%|████▋ | 14/30 [00:29<00:32, 2.06s/it] 50%|█████ | 15/30 [00:31<00:30, 2.06s/it] 53%|█████▎ | 16/30 [00:33<00:28, 2.06s/it] 57%|█████▋ | 17/30 [00:35<00:26, 2.06s/it] 60%|██████ | 18/30 [00:38<00:24, 2.06s/it] 63%|██████▎ | 19/30 [00:40<00:22, 2.06s/it] 67%|██████▋ | 20/30 [00:42<00:20, 2.05s/it] 70%|███████ | 21/30 [00:44<00:18, 2.05s/it] 73%|███████▎ | 22/30 [00:46<00:16, 2.04s/it] 77%|███████▋ | 23/30 [00:48<00:14, 2.04s/it] 80%|████████ | 24/30 [00:50<00:12, 2.04s/it] 83%|████████▎ | 25/30 [00:52<00:10, 2.03s/it] 87%|████████▋ | 26/30 [00:54<00:08, 2.03s/it] 90%|█████████ | 27/30 [00:56<00:06, 2.03s/it] 93%|█████████▎| 28/30 [00:58<00:04, 2.03s/it] 97%|█████████▋| 29/30 [01:00<00:02, 2.03s/it] 100%|██████████| 30/30 [01:02<00:00, 2.03s/it] 100%|██████████| 30/30 [01:02<00:00, 2.08s/it] Decoding latents in cuda:0... done in 3.33s Move latents to cpu... done in 0.04s 0: 640x640 1 face, 8.1ms Speed: 4.0ms preprocess, 8.1ms inference, 28.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.61it/s] 20%|██ | 2/10 [00:01<00:04, 1.64it/s] 30%|███ | 3/10 [00:01<00:04, 1.66it/s] 40%|████ | 4/10 [00:02<00:03, 1.66it/s] 50%|█████ | 5/10 [00:03<00:03, 1.66it/s] 60%|██████ | 6/10 [00:03<00:02, 1.67it/s] 70%|███████ | 7/10 [00:04<00:01, 1.66it/s] 80%|████████ | 8/10 [00:04<00:01, 1.67it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.66it/s] 100%|██████████| 10/10 [00:06<00:00, 1.67it/s] 100%|██████████| 10/10 [00:06<00:00, 1.66it/s] Decoding latents in cuda:0... done in 1.1s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.3ms Speed: 3.1ms preprocess, 7.3ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.71it/s] 20%|██ | 2/10 [00:01<00:04, 1.67it/s] 30%|███ | 3/10 [00:01<00:04, 1.68it/s] 40%|████ | 4/10 [00:02<00:03, 1.66it/s] 50%|█████ | 5/10 [00:03<00:03, 1.66it/s] 60%|██████ | 6/10 [00:03<00:02, 1.66it/s] 70%|███████ | 7/10 [00:04<00:01, 1.65it/s] 80%|████████ | 8/10 [00:04<00:01, 1.66it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.65it/s] 100%|██████████| 10/10 [00:06<00:00, 1.65it/s] 100%|██████████| 10/10 [00:06<00:00, 1.66it/s] Decoding latents in cuda:0... done in 1.11s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.3ms preprocess, 7.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.4ms Speed: 3.2ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.70it/s] 20%|██ | 2/10 [00:01<00:04, 1.65it/s] 30%|███ | 3/10 [00:01<00:04, 1.66it/s] 40%|████ | 4/10 [00:02<00:03, 1.64it/s] 50%|█████ | 5/10 [00:03<00:03, 1.64it/s] 60%|██████ | 6/10 [00:03<00:02, 1.64it/s] 70%|███████ | 7/10 [00:04<00:01, 1.63it/s] 80%|████████ | 8/10 [00:04<00:01, 1.63it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.63it/s] 100%|██████████| 10/10 [00:06<00:00, 1.63it/s] 100%|██████████| 10/10 [00:06<00:00, 1.64it/s] Decoding latents in cuda:0... done in 1.12s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 8.4ms Speed: 3.1ms preprocess, 8.4ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.
prompt *
Specify things to see in the output
negative_prompt
Specify things to not see in the output
num_outputs
Number of output images
width
Output image width
height
Output image height
enhance_face_with_adetailer
Enhance face with adetailer
enhance_hands_with_adetailer
Enhance hands with adetailer
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
detail
Enhance/diminish detail while keeping the overall style/character
brightness
Adjust brightness
contrast
Adjust contrast
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
input_image
Base image that the output should be generated from. This is useful when you want to add some detail to input_image. For example, if prompt is "sunglasses" and input_image has a man, there is the man wearing sunglasses in the output.
input_image_redrawing_strength
How differ the output is from input_image. Used only when input_image is given.
reference_image
Image with which the output should share identity (e.g. face of a person or type of a dog)
reference_image_strength
Strength of applying reference_image. Used only when reference_image is given.
reference_pose_image
Image with a reference pose
reference_pose_strength
Strength of applying reference_pose_image. Used only when reference_pose_image is given.
reference_depth_image
Image with a reference depth
reference_depth_strength
Strength of applying reference_depth_image. Used only when reference_depth_image is given.
sampler
Sampler type
samping_steps
Number of denoising steps
cfg_scale
Scale for classifier-free guidance
clip_skip
The number of last layers of CLIP network to skip
vae
Select VAE
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_2
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
lora_3
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
embedding_1
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
Sign in to run this model for free!
https://files.tungsten.run/uploads/d958950f2ed2421db6f38ed18f000924/00000-240075782.webp
https://files.tungsten.run/uploads/2237f646209542aeba5760dcefb1ebe9/00001-240075783.webp
https://files.tungsten.run/uploads/882eb5a3175647409be9e5287edae34f/00002-240075784.webp
This example was created by sparks
Finished in 104.8 seconds
Setting up the model... Preparing inputs... Processing... Using seed 240075782 Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: fashion photography of topless white elven girl, Cara Delevingne, with medium breasts, with short ears, pink nipples, perky nipples, in a forest, symmetrical, octane render, 35mm, bokeh, 9:16, (intricate details:1.12), hdr, (intricate details, hyperdetailed:1.15), (natural skin texture, hyperrealism, soft light, sharp:1.2), look at the camera, demure, <lora:add-detail-xl:1.5> Full negative prompt: (worst quality:2, low quality:2), (deformed, distorted, disfigured), (bad eyes, wrong lips, weird mouth, bad teeth, mutated hands and fingers:1.2), (bad anatomy), wrong anatomy, amputation, extra limb, missing limb, floating limbs, disconnected limbs, mutation, ugly, disgusting, (signature, watermark, username, blurry, artist name), asian 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:03<01:28, 3.05s/it] 7%|▋ | 2/30 [00:05<01:08, 2.45s/it] 10%|█ | 3/30 [00:07<01:01, 2.26s/it] 13%|█▎ | 4/30 [00:09<00:56, 2.18s/it] 17%|█▋ | 5/30 [00:11<00:53, 2.13s/it] 20%|██ | 6/30 [00:13<00:50, 2.11s/it] 23%|██▎ | 7/30 [00:15<00:48, 2.09s/it] 27%|██▋ | 8/30 [00:17<00:45, 2.08s/it] 30%|███ | 9/30 [00:19<00:43, 2.07s/it] 33%|███▎ | 10/30 [00:21<00:41, 2.07s/it] 37%|███▋ | 11/30 [00:23<00:39, 2.07s/it] 40%|████ | 12/30 [00:25<00:37, 2.06s/it] 43%|████▎ | 13/30 [00:27<00:35, 2.06s/it] 47%|████▋ | 14/30 [00:29<00:32, 2.06s/it] 50%|█████ | 15/30 [00:31<00:30, 2.06s/it] 53%|█████▎ | 16/30 [00:33<00:28, 2.06s/it] 57%|█████▋ | 17/30 [00:35<00:26, 2.06s/it] 60%|██████ | 18/30 [00:38<00:24, 2.06s/it] 63%|██████▎ | 19/30 [00:40<00:22, 2.06s/it] 67%|██████▋ | 20/30 [00:42<00:20, 2.05s/it] 70%|███████ | 21/30 [00:44<00:18, 2.05s/it] 73%|███████▎ | 22/30 [00:46<00:16, 2.04s/it] 77%|███████▋ | 23/30 [00:48<00:14, 2.04s/it] 80%|████████ | 24/30 [00:50<00:12, 2.04s/it] 83%|████████▎ | 25/30 [00:52<00:10, 2.03s/it] 87%|████████▋ | 26/30 [00:54<00:08, 2.03s/it] 90%|█████████ | 27/30 [00:56<00:06, 2.03s/it] 93%|█████████▎| 28/30 [00:58<00:04, 2.03s/it] 97%|█████████▋| 29/30 [01:00<00:02, 2.03s/it] 100%|██████████| 30/30 [01:02<00:00, 2.03s/it] 100%|██████████| 30/30 [01:02<00:00, 2.08s/it] Decoding latents in cuda:0... done in 3.33s Move latents to cpu... done in 0.04s 0: 640x640 1 face, 8.1ms Speed: 4.0ms preprocess, 8.1ms inference, 28.6ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.61it/s] 20%|██ | 2/10 [00:01<00:04, 1.64it/s] 30%|███ | 3/10 [00:01<00:04, 1.66it/s] 40%|████ | 4/10 [00:02<00:03, 1.66it/s] 50%|█████ | 5/10 [00:03<00:03, 1.66it/s] 60%|██████ | 6/10 [00:03<00:02, 1.67it/s] 70%|███████ | 7/10 [00:04<00:01, 1.66it/s] 80%|████████ | 8/10 [00:04<00:01, 1.67it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.66it/s] 100%|██████████| 10/10 [00:06<00:00, 1.67it/s] 100%|██████████| 10/10 [00:06<00:00, 1.66it/s] Decoding latents in cuda:0... done in 1.1s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.3ms Speed: 3.1ms preprocess, 7.3ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x640 1 face, 7.3ms Speed: 3.2ms preprocess, 7.3ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.71it/s] 20%|██ | 2/10 [00:01<00:04, 1.67it/s] 30%|███ | 3/10 [00:01<00:04, 1.68it/s] 40%|████ | 4/10 [00:02<00:03, 1.66it/s] 50%|█████ | 5/10 [00:03<00:03, 1.66it/s] 60%|██████ | 6/10 [00:03<00:02, 1.66it/s] 70%|███████ | 7/10 [00:04<00:01, 1.65it/s] 80%|████████ | 8/10 [00:04<00:01, 1.66it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.65it/s] 100%|██████████| 10/10 [00:06<00:00, 1.65it/s] 100%|██████████| 10/10 [00:06<00:00, 1.66it/s] Decoding latents in cuda:0... done in 1.11s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 7.2ms Speed: 3.3ms preprocess, 7.2ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x640 1 face, 7.4ms Speed: 3.2ms preprocess, 7.4ms inference, 1.4ms postprocess per image at shape (1, 3, 640, 640) 0%| | 0/10 [00:00<?, ?it/s] 10%|█ | 1/10 [00:00<00:05, 1.70it/s] 20%|██ | 2/10 [00:01<00:04, 1.65it/s] 30%|███ | 3/10 [00:01<00:04, 1.66it/s] 40%|████ | 4/10 [00:02<00:03, 1.64it/s] 50%|█████ | 5/10 [00:03<00:03, 1.64it/s] 60%|██████ | 6/10 [00:03<00:02, 1.64it/s] 70%|███████ | 7/10 [00:04<00:01, 1.63it/s] 80%|████████ | 8/10 [00:04<00:01, 1.63it/s] 90%|█████████ | 9/10 [00:05<00:00, 1.63it/s] 100%|██████████| 10/10 [00:06<00:00, 1.63it/s] 100%|██████████| 10/10 [00:06<00:00, 1.64it/s] Decoding latents in cuda:0... done in 1.12s Move latents to cpu... done in 0.0s 0: 640x640 (no detections), 8.4ms Speed: 3.1ms preprocess, 8.4ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640) [-] ADetailer: nothing detected on image 3 with 2nd settings. Uploading outputs... Finished.