tungsten-logo
Sign In
digital-dream-xl
digital-dream-xl

digital-dream-xl

12 stars
Version: be0407f
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/e3fdfa06229f4262ac86e0ec181c1238/00000-993554368.webp
https://files.tungsten.run/uploads/42a00db7a0e84f568028d23c79bcdecb/00001-993554369.webp
https://files.tungsten.run/uploads/255793527e124718969e7287d572c85f/00002-993554370.webp
This example was created by evevalentine2017
Finished in 160.5 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photography in the style of detailed hyperrealism, cinematic composition, dramatic light, painted crescent moon in the sky, expressive, hyper detailed, intricate,poster, artstation Full negative prompt: desaturated, old, baggy eyes, tired, simple background, large breasts, clones, twins, 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:01<02:05, 1.59s/it] 2%|▎ | 2/80 [00:03<02:25, 1.86s/it] 4%|▍ | 3/80 [00:05<02:31, 1.97s/it] 5%|▌ | 4/80 [00:07<02:33, 2.02s/it] 6%|▋ | 5/80 [00:09<02:33, 2.05s/it] 8%|▊ | 6/80 [00:11<02:29, 2.03s/it] 9%|▉ | 7/80 [00:13<02:25, 2.00s/it] 10%|█ | 8/80 [00:15<02:24, 2.01s/it] 11%|█▏ | 9/80 [00:18<02:25, 2.05s/it] 12%|█▎ | 10/80 [00:20<02:23, 2.04s/it] 14%|█▍ | 11/80 [00:22<02:22, 2.06s/it] 15%|█▌ | 12/80 [00:24<02:18, 2.04s/it] 16%|█▋ | 13/80 [00:26<02:16, 2.04s/it] 18%|█▊ | 14/80 [00:28<02:14, 2.04s/it] 19%|█▉ | 15/80 [00:30<02:11, 2.02s/it] 20%|██ | 16/80 [00:32<02:10, 2.04s/it] 21%|██▏ | 17/80 [00:34<02:08, 2.03s/it] 22%|██▎ | 18/80 [00:36<02:07, 2.06s/it] 24%|██▍ | 19/80 [00:38<02:04, 2.04s/it] 25%|██▌ | 20/80 [00:40<02:03, 2.05s/it] 26%|██▋ | 21/80 [00:42<01:59, 2.03s/it] 28%|██▊ | 22/80 [00:44<01:58, 2.04s/it] 29%|██▉ | 23/80 [00:46<01:57, 2.06s/it] 30%|███ | 24/80 [00:48<01:55, 2.07s/it] 31%|███▏ | 25/80 [00:50<01:51, 2.03s/it] 32%|███▎ | 26/80 [00:52<01:50, 2.05s/it] 34%|███▍ | 27/80 [00:54<01:48, 2.04s/it] 35%|███▌ | 28/80 [00:56<01:45, 2.02s/it] 36%|███▋ | 29/80 [00:58<01:45, 2.07s/it] 38%|███▊ | 30/80 [01:00<01:40, 2.00s/it] 39%|███▉ | 31/80 [01:02<01:38, 2.02s/it] 40%|████ | 32/80 [01:04<01:33, 1.96s/it] 41%|████▏ | 33/80 [01:06<01:31, 1.95s/it] 42%|████▎ | 34/80 [01:08<01:29, 1.94s/it] 44%|████▍ | 35/80 [01:10<01:26, 1.92s/it] 45%|████▌ | 36/80 [01:12<01:26, 1.96s/it] 46%|████▋ | 37/80 [01:14<01:21, 1.90s/it] 48%|████▊ | 38/80 [01:16<01:19, 1.89s/it] 49%|████▉ | 39/80 [01:18<01:19, 1.94s/it] 50%|█████ | 40/80 [01:20<01:17, 1.93s/it] 51%|█████▏ | 41/80 [01:21<01:14, 1.92s/it] 52%|█████▎ | 42/80 [01:23<01:14, 1.95s/it] 54%|█████▍ | 43/80 [01:25<01:10, 1.91s/it] 55%|█████▌ | 44/80 [01:27<01:10, 1.96s/it] 56%|█████▋ | 45/80 [01:29<01:07, 1.93s/it] 57%|█████▊ | 46/80 [01:31<01:05, 1.92s/it] 59%|█████▉ | 47/80 [01:33<01:01, 1.87s/it] 60%|██████ | 48/80 [01:35<01:01, 1.91s/it] 61%|██████▏ | 49/80 [01:37<00:58, 1.90s/it] 62%|██████▎ | 50/80 [01:39<00:56, 1.89s/it] 64%|██████▍ | 51/80 [01:41<00:55, 1.90s/it] 65%|██████▌ | 52/80 [01:43<00:54, 1.94s/it] 66%|██████▋ | 53/80 [01:44<00:50, 1.85s/it] 68%|██████▊ | 54/80 [01:46<00:46, 1.79s/it] 69%|██████▉ | 55/80 [01:48<00:44, 1.77s/it] 70%|███████ | 56/80 [01:50<00:44, 1.84s/it] 71%|███████▏ | 57/80 [01:51<00:42, 1.83s/it] 72%|███████▎ | 58/80 [01:53<00:39, 1.80s/it] 74%|███████▍ | 59/80 [01:55<00:37, 1.77s/it] 75%|███████▌ | 60/80 [01:57<00:36, 1.81s/it] 76%|███████▋ | 61/80 [01:59<00:34, 1.81s/it] 78%|███████▊ | 62/80 [02:00<00:31, 1.76s/it] 79%|███████▉ | 63/80 [02:02<00:30, 1.81s/it] 80%|████████ | 64/80 [02:04<00:28, 1.77s/it] 81%|████████▏ | 65/80 [02:05<00:26, 1.74s/it] 82%|████████▎ | 66/80 [02:07<00:25, 1.83s/it] 84%|████████▍ | 67/80 [02:09<00:23, 1.81s/it] 85%|████████▌ | 68/80 [02:11<00:22, 1.84s/it] 86%|████████▋ | 69/80 [02:13<00:19, 1.77s/it] 88%|████████▊ | 70/80 [02:15<00:17, 1.80s/it] 89%|████████▉ | 71/80 [02:16<00:15, 1.74s/it] 90%|█████████ | 72/80 [02:18<00:13, 1.66s/it] 91%|█████████▏| 73/80 [02:20<00:12, 1.72s/it] 92%|█████████▎| 74/80 [02:21<00:09, 1.65s/it] 94%|█████████▍| 75/80 [02:23<00:08, 1.68s/it] 95%|█████████▌| 76/80 [02:24<00:06, 1.66s/it] 96%|█████████▋| 77/80 [02:26<00:05, 1.70s/it] 98%|█████████▊| 78/80 [02:28<00:03, 1.68s/it] 99%|█████████▉| 79/80 [02:29<00:01, 1.50s/it] 100%|██████████| 80/80 [02:30<00:00, 1.34s/it] 100%|██████████| 80/80 [02:30<00:00, 1.88s/it] Decoding latents in cuda:0... done in 1.77s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 161.2ms Speed: 3.2ms preprocess, 161.2ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st 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), 7.9ms 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. 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/e3fdfa06229f4262ac86e0ec181c1238/00000-993554368.webp
https://files.tungsten.run/uploads/42a00db7a0e84f568028d23c79bcdecb/00001-993554369.webp
https://files.tungsten.run/uploads/255793527e124718969e7287d572c85f/00002-993554370.webp
This example was created by evevalentine2017
Finished in 160.5 seconds
Setting up the model... Preparing inputs... Processing... Loading VAE weight: models/VAE/sdxl_vae.safetensors Full prompt: photography in the style of detailed hyperrealism, cinematic composition, dramatic light, painted crescent moon in the sky, expressive, hyper detailed, intricate,poster, artstation Full negative prompt: desaturated, old, baggy eyes, tired, simple background, large breasts, clones, twins, 0%| | 0/80 [00:00<?, ?it/s] 1%|▏ | 1/80 [00:01<02:05, 1.59s/it] 2%|▎ | 2/80 [00:03<02:25, 1.86s/it] 4%|▍ | 3/80 [00:05<02:31, 1.97s/it] 5%|▌ | 4/80 [00:07<02:33, 2.02s/it] 6%|▋ | 5/80 [00:09<02:33, 2.05s/it] 8%|▊ | 6/80 [00:11<02:29, 2.03s/it] 9%|▉ | 7/80 [00:13<02:25, 2.00s/it] 10%|█ | 8/80 [00:15<02:24, 2.01s/it] 11%|█▏ | 9/80 [00:18<02:25, 2.05s/it] 12%|█▎ | 10/80 [00:20<02:23, 2.04s/it] 14%|█▍ | 11/80 [00:22<02:22, 2.06s/it] 15%|█▌ | 12/80 [00:24<02:18, 2.04s/it] 16%|█▋ | 13/80 [00:26<02:16, 2.04s/it] 18%|█▊ | 14/80 [00:28<02:14, 2.04s/it] 19%|█▉ | 15/80 [00:30<02:11, 2.02s/it] 20%|██ | 16/80 [00:32<02:10, 2.04s/it] 21%|██▏ | 17/80 [00:34<02:08, 2.03s/it] 22%|██▎ | 18/80 [00:36<02:07, 2.06s/it] 24%|██▍ | 19/80 [00:38<02:04, 2.04s/it] 25%|██▌ | 20/80 [00:40<02:03, 2.05s/it] 26%|██▋ | 21/80 [00:42<01:59, 2.03s/it] 28%|██▊ | 22/80 [00:44<01:58, 2.04s/it] 29%|██▉ | 23/80 [00:46<01:57, 2.06s/it] 30%|███ | 24/80 [00:48<01:55, 2.07s/it] 31%|███▏ | 25/80 [00:50<01:51, 2.03s/it] 32%|███▎ | 26/80 [00:52<01:50, 2.05s/it] 34%|███▍ | 27/80 [00:54<01:48, 2.04s/it] 35%|███▌ | 28/80 [00:56<01:45, 2.02s/it] 36%|███▋ | 29/80 [00:58<01:45, 2.07s/it] 38%|███▊ | 30/80 [01:00<01:40, 2.00s/it] 39%|███▉ | 31/80 [01:02<01:38, 2.02s/it] 40%|████ | 32/80 [01:04<01:33, 1.96s/it] 41%|████▏ | 33/80 [01:06<01:31, 1.95s/it] 42%|████▎ | 34/80 [01:08<01:29, 1.94s/it] 44%|████▍ | 35/80 [01:10<01:26, 1.92s/it] 45%|████▌ | 36/80 [01:12<01:26, 1.96s/it] 46%|████▋ | 37/80 [01:14<01:21, 1.90s/it] 48%|████▊ | 38/80 [01:16<01:19, 1.89s/it] 49%|████▉ | 39/80 [01:18<01:19, 1.94s/it] 50%|█████ | 40/80 [01:20<01:17, 1.93s/it] 51%|█████▏ | 41/80 [01:21<01:14, 1.92s/it] 52%|█████▎ | 42/80 [01:23<01:14, 1.95s/it] 54%|█████▍ | 43/80 [01:25<01:10, 1.91s/it] 55%|█████▌ | 44/80 [01:27<01:10, 1.96s/it] 56%|█████▋ | 45/80 [01:29<01:07, 1.93s/it] 57%|█████▊ | 46/80 [01:31<01:05, 1.92s/it] 59%|█████▉ | 47/80 [01:33<01:01, 1.87s/it] 60%|██████ | 48/80 [01:35<01:01, 1.91s/it] 61%|██████▏ | 49/80 [01:37<00:58, 1.90s/it] 62%|██████▎ | 50/80 [01:39<00:56, 1.89s/it] 64%|██████▍ | 51/80 [01:41<00:55, 1.90s/it] 65%|██████▌ | 52/80 [01:43<00:54, 1.94s/it] 66%|██████▋ | 53/80 [01:44<00:50, 1.85s/it] 68%|██████▊ | 54/80 [01:46<00:46, 1.79s/it] 69%|██████▉ | 55/80 [01:48<00:44, 1.77s/it] 70%|███████ | 56/80 [01:50<00:44, 1.84s/it] 71%|███████▏ | 57/80 [01:51<00:42, 1.83s/it] 72%|███████▎ | 58/80 [01:53<00:39, 1.80s/it] 74%|███████▍ | 59/80 [01:55<00:37, 1.77s/it] 75%|███████▌ | 60/80 [01:57<00:36, 1.81s/it] 76%|███████▋ | 61/80 [01:59<00:34, 1.81s/it] 78%|███████▊ | 62/80 [02:00<00:31, 1.76s/it] 79%|███████▉ | 63/80 [02:02<00:30, 1.81s/it] 80%|████████ | 64/80 [02:04<00:28, 1.77s/it] 81%|████████▏ | 65/80 [02:05<00:26, 1.74s/it] 82%|████████▎ | 66/80 [02:07<00:25, 1.83s/it] 84%|████████▍ | 67/80 [02:09<00:23, 1.81s/it] 85%|████████▌ | 68/80 [02:11<00:22, 1.84s/it] 86%|████████▋ | 69/80 [02:13<00:19, 1.77s/it] 88%|████████▊ | 70/80 [02:15<00:17, 1.80s/it] 89%|████████▉ | 71/80 [02:16<00:15, 1.74s/it] 90%|█████████ | 72/80 [02:18<00:13, 1.66s/it] 91%|█████████▏| 73/80 [02:20<00:12, 1.72s/it] 92%|█████████▎| 74/80 [02:21<00:09, 1.65s/it] 94%|█████████▍| 75/80 [02:23<00:08, 1.68s/it] 95%|█████████▌| 76/80 [02:24<00:06, 1.66s/it] 96%|█████████▋| 77/80 [02:26<00:05, 1.70s/it] 98%|█████████▊| 78/80 [02:28<00:03, 1.68s/it] 99%|█████████▉| 79/80 [02:29<00:01, 1.50s/it] 100%|██████████| 80/80 [02:30<00:00, 1.34s/it] 100%|██████████| 80/80 [02:30<00:00, 1.88s/it] Decoding latents in cuda:0... done in 1.77s Move latents to cpu... done in 0.02s 0: 640x480 (no detections), 161.2ms Speed: 3.2ms preprocess, 161.2ms inference, 1.2ms postprocess per image at shape (1, 3, 640, 480) [-] ADetailer: nothing detected on image 1 with 1st 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), 7.9ms 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. Uploading outputs... Finished.