tungsten-logo
Sign In
Cats Inside Bubbles with Tamarin XL
tamarin-xl:v1.0
evevalentine2017
evevalentine2017
·
Feb 3
356
Input
prompt
Specify things to see in the output
oil painting of "Fairytale", a bubble coming out of an open book, the bubble contains a fantasy world, hyperdetailed double exposure fantasy illustration, masterpiece, cinematic, by Andreas Lie, Luke Gram, photorealism, backlit, gorgeous light, cat, <lora:tweak-detail-xl:2>
negative_prompt
Specify things to not see in the output
letters, words, signature, (portrait), (close up)
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2816015102
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
40
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
None
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
tweak-detail-xl.safetensors
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)
badhandv4.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
negative_hand-neg.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
Output
https://files.tungsten.run/uploads/8037d76e57f9419ea19b4840df46d4dd/00000-2816015102.webp
https://files.tungsten.run/uploads/1fcbf36661fe4c96879115ae9e66ba68/00001-2816015103.webp
https://files.tungsten.run/uploads/c771085e96634874bc03129618312a8e/00002-2816015104.webp
Finished in 61.4 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: oil painting of "Fairytale", a bubble coming out of an open book, the bubble contains a fantasy world, hyperdetailed double exposure fantasy illustration, masterpiece, cinematic, by Andreas Lie, Luke Gram, photorealism, backlit, gorgeous light, cat, <lora:tweak-detail-xl:2> Full negative prompt: letters, words, signature, (portrait), (close up) 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:02<01:27, 2.25s/it] 5%|▌ | 2/40 [00:03<00:56, 1.48s/it] 8%|▊ | 3/40 [00:04<00:45, 1.23s/it] 10%|█ | 4/40 [00:05<00:40, 1.12s/it] 12%|█▎ | 5/40 [00:06<00:36, 1.05s/it] 15%|█▌ | 6/40 [00:06<00:34, 1.02s/it] 18%|█▊ | 7/40 [00:07<00:32, 1.01it/s] 20%|██ | 8/40 [00:08<00:31, 1.02it/s] 22%|██▎ | 9/40 [00:09<00:30, 1.03it/s] 25%|██▌ | 10/40 [00:10<00:28, 1.04it/s] 28%|██▊ | 11/40 [00:11<00:27, 1.04it/s] 30%|███ | 12/40 [00:12<00:26, 1.04it/s] 32%|███▎ | 13/40 [00:13<00:25, 1.05it/s] 35%|███▌ | 14/40 [00:14<00:24, 1.05it/s] 38%|███▊ | 15/40 [00:15<00:23, 1.04it/s] 40%|████ | 16/40 [00:16<00:22, 1.04it/s] 42%|████▎ | 17/40 [00:17<00:22, 1.04it/s] 45%|████▌ | 18/40 [00:18<00:21, 1.04it/s] 48%|████▊ | 19/40 [00:19<00:20, 1.04it/s] 50%|█████ | 20/40 [00:20<00:19, 1.04it/s] 52%|█████▎ | 21/40 [00:21<00:18, 1.04it/s] 55%|█████▌ | 22/40 [00:22<00:17, 1.04it/s] 57%|█████▊ | 23/40 [00:23<00:16, 1.03it/s] 60%|██████ | 24/40 [00:24<00:15, 1.04it/s] 62%|██████▎ | 25/40 [00:25<00:14, 1.03it/s] 65%|██████▌ | 26/40 [00:26<00:13, 1.03it/s] 68%|██████▊ | 27/40 [00:27<00:12, 1.03it/s] 70%|███████ | 28/40 [00:28<00:11, 1.03it/s] 72%|███████▎ | 29/40 [00:29<00:10, 1.03it/s] 75%|███████▌ | 30/40 [00:30<00:09, 1.03it/s] 78%|███████▊ | 31/40 [00:30<00:08, 1.03it/s] 80%|████████ | 32/40 [00:31<00:07, 1.03it/s] 82%|████████▎ | 33/40 [00:32<00:06, 1.02it/s] 85%|████████▌ | 34/40 [00:33<00:05, 1.02it/s] 88%|████████▊ | 35/40 [00:34<00:04, 1.02it/s] 90%|█████████ | 36/40 [00:35<00:03, 1.02it/s] 92%|█████████▎| 37/40 [00:36<00:02, 1.02it/s] 95%|█████████▌| 38/40 [00:37<00:01, 1.02it/s] 98%|█████████▊| 39/40 [00:38<00:00, 1.02it/s] 100%|██████████| 40/40 [00:39<00:00, 1.02it/s] 100%|██████████| 40/40 [00:39<00:00, 1.00it/s] Decoding latents in cuda:0... done in 1.72s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 166.4ms Speed: 2.8ms preprocess, 166.4ms inference, 6.1ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x480 (no detections), 114.4ms Speed: 3.2ms preprocess, 114.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x480 (no detections), 8.0ms Speed: 2.4ms preprocess, 8.0ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x480 (no detections), 7.7ms Speed: 2.3ms preprocess, 7.7ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x480 (no detections), 7.9ms Speed: 2.3ms preprocess, 7.9ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x480 1 hand, 8.0ms Speed: 3.1ms preprocess, 8.0ms inference, 10.8ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:08, 2.18it/s] 11%|█ | 2/19 [00:00<00:06, 2.61it/s] 16%|█▌ | 3/19 [00:01<00:05, 2.78it/s] 21%|██ | 4/19 [00:01<00:05, 2.88it/s] 26%|██▋ | 5/19 [00:01<00:04, 2.92it/s] 32%|███▏ | 6/19 [00:02<00:04, 2.94it/s] 37%|███▋ | 7/19 [00:02<00:04, 2.97it/s] 42%|████▏ | 8/19 [00:02<00:03, 2.98it/s] 47%|████▋ | 9/19 [00:03<00:03, 2.99it/s] 53%|█████▎ | 10/19 [00:03<00:03, 3.00it/s] 58%|█████▊ | 11/19 [00:03<00:02, 3.02it/s] 63%|██████▎ | 12/19 [00:04<00:02, 3.00it/s] 68%|██████▊ | 13/19 [00:04<00:02, 2.96it/s] 74%|███████▎ | 14/19 [00:04<00:01, 2.98it/s] 79%|███████▉ | 15/19 [00:05<00:01, 3.00it/s] 84%|████████▍ | 16/19 [00:05<00:01, 3.00it/s] 89%|████████▉ | 17/19 [00:05<00:00, 3.02it/s] 95%|█████████▍| 18/19 [00:06<00:00, 3.02it/s] 100%|██████████| 19/19 [00:06<00:00, 2.97it/s] 100%|██████████| 19/19 [00:06<00:00, 2.94it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s Uploading outputs... Finished.
prompt
Specify things to see in the output
oil painting of "Fairytale", a bubble coming out of an open book, the bubble contains a fantasy world, hyperdetailed double exposure fantasy illustration, masterpiece, cinematic, by Andreas Lie, Luke Gram, photorealism, backlit, gorgeous light, cat, <lora:tweak-detail-xl:2>
negative_prompt
Specify things to not see in the output
letters, words, signature, (portrait), (close up)
num_outputs
Number of output images
3
width
Output image width
768
height
Output image height
1024
enhance_face_with_adetailer
Enhance face with adetailer
true
enhance_hands_with_adetailer
Enhance hands with adetailer
true
adetailer_denoising_strength
1: completely redraw face or hands / 0: no effect on output images
0.45
detail
Enhance/diminish detail while keeping the overall style/character
0
brightness
Adjust brightness
0
contrast
Adjust contrast
0
seed
Same seed with the same prompt generates the same image. Set as -1 to randomize output.
2816015102
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.
0.55
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.
1
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.
1
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.
1
sampler
Sampler type
DPM++ 2M Karras
samping_steps
Number of denoising steps
40
cfg_scale
Scale for classifier-free guidance
5
clip_skip
The number of last layers of CLIP network to skip
2
vae
Select VAE
None
lora_1
LoRA file. Apply by writing the following in prompt: <lora:FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE>
tweak-detail-xl.safetensors
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)
badhandv4.pt
embedding_2
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
bad-hands-5.pt
embedding_3
Embedding file (textural inversion). Apply by writing the following in prompt or negative prompt: (FILE_NAME_WITHOUT_EXTENSION:MAGNITUDE)
negative_hand-neg.pt
disable_prompt_modification
Disable automatically adding suggested prompt modification. Built-in LoRAs and trigger words will remain.
false
https://files.tungsten.run/uploads/8037d76e57f9419ea19b4840df46d4dd/00000-2816015102.webp
https://files.tungsten.run/uploads/1fcbf36661fe4c96879115ae9e66ba68/00001-2816015103.webp
https://files.tungsten.run/uploads/c771085e96634874bc03129618312a8e/00002-2816015104.webp
Finished in 61.4 seconds
Setting up the model... Preparing inputs... Processing... Full prompt: oil painting of "Fairytale", a bubble coming out of an open book, the bubble contains a fantasy world, hyperdetailed double exposure fantasy illustration, masterpiece, cinematic, by Andreas Lie, Luke Gram, photorealism, backlit, gorgeous light, cat, <lora:tweak-detail-xl:2> Full negative prompt: letters, words, signature, (portrait), (close up) 0%| | 0/40 [00:00<?, ?it/s] 2%|▎ | 1/40 [00:02<01:27, 2.25s/it] 5%|▌ | 2/40 [00:03<00:56, 1.48s/it] 8%|▊ | 3/40 [00:04<00:45, 1.23s/it] 10%|█ | 4/40 [00:05<00:40, 1.12s/it] 12%|█▎ | 5/40 [00:06<00:36, 1.05s/it] 15%|█▌ | 6/40 [00:06<00:34, 1.02s/it] 18%|█▊ | 7/40 [00:07<00:32, 1.01it/s] 20%|██ | 8/40 [00:08<00:31, 1.02it/s] 22%|██▎ | 9/40 [00:09<00:30, 1.03it/s] 25%|██▌ | 10/40 [00:10<00:28, 1.04it/s] 28%|██▊ | 11/40 [00:11<00:27, 1.04it/s] 30%|███ | 12/40 [00:12<00:26, 1.04it/s] 32%|███▎ | 13/40 [00:13<00:25, 1.05it/s] 35%|███▌ | 14/40 [00:14<00:24, 1.05it/s] 38%|███▊ | 15/40 [00:15<00:23, 1.04it/s] 40%|████ | 16/40 [00:16<00:22, 1.04it/s] 42%|████▎ | 17/40 [00:17<00:22, 1.04it/s] 45%|████▌ | 18/40 [00:18<00:21, 1.04it/s] 48%|████▊ | 19/40 [00:19<00:20, 1.04it/s] 50%|█████ | 20/40 [00:20<00:19, 1.04it/s] 52%|█████▎ | 21/40 [00:21<00:18, 1.04it/s] 55%|█████▌ | 22/40 [00:22<00:17, 1.04it/s] 57%|█████▊ | 23/40 [00:23<00:16, 1.03it/s] 60%|██████ | 24/40 [00:24<00:15, 1.04it/s] 62%|██████▎ | 25/40 [00:25<00:14, 1.03it/s] 65%|██████▌ | 26/40 [00:26<00:13, 1.03it/s] 68%|██████▊ | 27/40 [00:27<00:12, 1.03it/s] 70%|███████ | 28/40 [00:28<00:11, 1.03it/s] 72%|███████▎ | 29/40 [00:29<00:10, 1.03it/s] 75%|███████▌ | 30/40 [00:30<00:09, 1.03it/s] 78%|███████▊ | 31/40 [00:30<00:08, 1.03it/s] 80%|████████ | 32/40 [00:31<00:07, 1.03it/s] 82%|████████▎ | 33/40 [00:32<00:06, 1.02it/s] 85%|████████▌ | 34/40 [00:33<00:05, 1.02it/s] 88%|████████▊ | 35/40 [00:34<00:04, 1.02it/s] 90%|█████████ | 36/40 [00:35<00:03, 1.02it/s] 92%|█████████▎| 37/40 [00:36<00:02, 1.02it/s] 95%|█████████▌| 38/40 [00:37<00:01, 1.02it/s] 98%|█████████▊| 39/40 [00:38<00:00, 1.02it/s] 100%|██████████| 40/40 [00:39<00:00, 1.02it/s] 100%|██████████| 40/40 [00:39<00:00, 1.00it/s] Decoding latents in cuda:0... done in 1.72s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 166.4ms Speed: 2.8ms preprocess, 166.4ms inference, 6.1ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st settings. 0: 640x480 (no detections), 114.4ms Speed: 3.2ms preprocess, 114.4ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 2nd settings. 0: 640x480 (no detections), 8.0ms Speed: 2.4ms preprocess, 8.0ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 1st settings. 0: 640x480 (no detections), 7.7ms Speed: 2.3ms preprocess, 7.7ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 2 with 2nd settings. 0: 640x480 (no detections), 7.9ms Speed: 2.3ms preprocess, 7.9ms inference, 0.7ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 3 with 1st settings. 0: 640x480 1 hand, 8.0ms Speed: 3.1ms preprocess, 8.0ms inference, 10.8ms postprocess per image at shape (1, 3, 640, 480) 0%| | 0/19 [00:00<?, ?it/s] 5%|▌ | 1/19 [00:00<00:08, 2.18it/s] 11%|█ | 2/19 [00:00<00:06, 2.61it/s] 16%|█▌ | 3/19 [00:01<00:05, 2.78it/s] 21%|██ | 4/19 [00:01<00:05, 2.88it/s] 26%|██▋ | 5/19 [00:01<00:04, 2.92it/s] 32%|███▏ | 6/19 [00:02<00:04, 2.94it/s] 37%|███▋ | 7/19 [00:02<00:04, 2.97it/s] 42%|████▏ | 8/19 [00:02<00:03, 2.98it/s] 47%|████▋ | 9/19 [00:03<00:03, 2.99it/s] 53%|█████▎ | 10/19 [00:03<00:03, 3.00it/s] 58%|█████▊ | 11/19 [00:03<00:02, 3.02it/s] 63%|██████▎ | 12/19 [00:04<00:02, 3.00it/s] 68%|██████▊ | 13/19 [00:04<00:02, 2.96it/s] 74%|███████▎ | 14/19 [00:04<00:01, 2.98it/s] 79%|███████▉ | 15/19 [00:05<00:01, 3.00it/s] 84%|████████▍ | 16/19 [00:05<00:01, 3.00it/s] 89%|████████▉ | 17/19 [00:05<00:00, 3.02it/s] 95%|█████████▍| 18/19 [00:06<00:00, 3.02it/s] 100%|██████████| 19/19 [00:06<00:00, 2.97it/s] 100%|██████████| 19/19 [00:06<00:00, 2.94it/s] Decoding latents in cuda:0... done in 0.58s Move latents to cpu... done in 0.0s Uploading outputs... Finished.