Readme
An SDXL full model tune aimed at photorealism. https://huggingface.co/SG161222/RealVisXL_V3.0
fofr / realvisxl-v3
Amazing photorealism with RealVisXL_V3.0, based on SDXL, trainable
Github
Model's Last Updated: December 21 2023
Introduction of realvisxl-v3
Runs of fofr realvisxl-v3 on replicate.com
668.1K
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
15.9K
30-day runs
More Information About realvisxl-v3 replicate.com Model
Url of realvisxl-v3
realvisxl-v3 replicate.com Url
realvisxl-v3 Github
realvisxl-v3 Owner Github
Provider of realvisxl-v3 replicate.com
Other API from fofr
Turn a face into 3D, emoji, pixel art, video game, claymation or toy
Total runs:
12.3M
Run Growth:
200.0K
Growth Rate:
1.63%
An SDXL fine-tune based on Apple Emojis
Total runs:
8.6M
Run Growth:
300.0K
Growth Rate:
3.49%
Determines the toxicity of text to image prompts, llama-13b fine-tune. [SAFETY_RANKING] between 0 (safe) and 10 (toxic)
Total runs:
1.9M
Run Growth:
0
Growth Rate:
0.00%
Run any ComfyUI workflow. Guide: https://github.com/fofr/cog-comfyui
Total runs:
1.4M
Run Growth:
300.0K
Growth Rate:
21.43%
Turn a face into a sticker
Total runs:
1.3M
Run Growth:
0
Growth Rate:
0.00%
Super-fast, 0.6s per image. LCM with img2img, large batching and canny controlnet
Total runs:
1.3M
Run Growth:
100.0K
Growth Rate:
7.69%
RealVisXl V3 with multi-controlnet, lora loading, img2img, inpainting
Total runs:
1.2M
Run Growth:
100.0K
Growth Rate:
8.33%
Create images of a given character in different poses
Total runs:
827.1K
Run Growth:
42.2K
Growth Rate:
5.11%
A flux lora fine-tuned on black light images
Total runs:
816.0K
Run Growth:
127.5K
Growth Rate:
15.63%
Make stickers with AI. Generates graphics with transparent backgrounds.
Total runs:
672.9K
Run Growth:
70.7K
Growth Rate:
10.55%
Transfer the style of one image to another
Total runs:
597.0K
Run Growth:
55.9K
Growth Rate:
9.46%
Adapt any picture of a face into another image
Total runs:
444.4K
Run Growth:
22.2K
Growth Rate:
5.00%
Create a waveform video from audio
Total runs:
381.7K
Run Growth:
100
Growth Rate:
0.03%
Multi-controlnet, lora loading, img2img, inpainting
Total runs:
208.2K
Run Growth:
1.1K
Growth Rate:
0.53%
Fast and high quality lightning model, epiCRealismXL-Lightning Hades
Total runs:
157.2K
Run Growth:
2.6K
Growth Rate:
1.65%
Use a face to make images. Uses SDXL fine-tuned checkpoints.
Total runs:
152.7K
Run Growth:
5.4K
Growth Rate:
3.54%
Portrait animation using a driving video source
Total runs:
68.4K
Run Growth:
2.0K
Growth Rate:
2.92%
An SDXL fine-tuned on Dalle3 underwater imagery
Total runs:
59.8K
Run Growth:
0
Growth Rate:
0.00%
Quickly edit the expression of a face
Total runs:
55.7K
Run Growth:
4.5K
Growth Rate:
9.64%
Generate image prompts for Midjourney. Prefix inputs with "Image: "
Total runs:
53.7K
Run Growth:
100
Growth Rate:
0.19%
SDXL fine-tuned on photos of freshly inked tattoos
Total runs:
51.3K
Run Growth:
5.2K
Growth Rate:
10.14%
Create videos from illustrated input images
Total runs:
41.7K
Run Growth:
1.8K
Growth Rate:
4.33%
Create illusions with img2img and masking support
Total runs:
41.6K
Run Growth:
2.7K
Growth Rate:
6.49%
A fine-tuned SDXL lora based on the Barbie movie
Total runs:
38.7K
Run Growth:
1.1K
Growth Rate:
2.84%
Canny, soft edge, depth, lineart, segmentation, pose, etc
Total runs:
38.5K
Run Growth:
0
Growth Rate:
0.00%
Use a face to instantly make images. Uses SDXL Lightning checkpoints.
Total runs:
34.9K
Run Growth:
3.0K
Growth Rate:
8.60%
A model for experimenting with all the SD3 settings. Non-commercial use only, unless you have a Stability AI Self Hosted License.
Total runs:
32.0K
Run Growth:
0
Growth Rate:
0.00%
Fast animation using a latent consistency model
Total runs:
29.2K
Run Growth:
1.1K
Growth Rate:
3.77%
A large-scale text-to-image generation model based on latent diffusion, developed by the Kuaishou Kolors team
Total runs:
26.4K
Run Growth:
1.8K
Growth Rate:
6.84%
Stable Diffusion 3 medium with added variability in outputs. Non-commercial use only, unless you have a Stability AI Self Hosted License.
Total runs:
20.2K
Run Growth:
0
Growth Rate:
0.00%
Kolors with style transfer, composition transfer and other IPAdapter techniques
Total runs:
17.4K
Run Growth:
300
Growth Rate:
1.72%
SDXL fine-tuned on MJv6 Simpsons generated images
Total runs:
16.0K
Run Growth:
1.6K
Growth Rate:
10.00%
FLUX.1-dev with XLabs-AI’s realism lora
Total runs:
15.4K
Run Growth:
0
Growth Rate:
0.00%
LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched.
Total runs:
14.7K
Run Growth:
14.7K
Growth Rate:
99.81%
An SDXL fine-tune based on bad 2004 digital photography
Total runs:
13.4K
Run Growth:
0
Growth Rate:
0.00%
Split a video into frames
Total runs:
13.2K
Run Growth:
200
Growth Rate:
1.52%
Generate a video that morphs between subjects, with an optional style
Total runs:
12.9K
Run Growth:
300
Growth Rate:
2.33%
A fine-tuned SDXL lora based on Tron Legacy
Total runs:
12.8K
Run Growth:
0
Growth Rate:
0.00%
Many models: RealVisXL, Juggernaut, Proteus, DreamShaper, etc.
Total runs:
10.6K
Run Growth:
0
Growth Rate:
0.00%
Run any ComfyUI workflow on an A100. Guide: https://github.com/fofr/cog-comfyui
Total runs:
9.0K
Run Growth:
1.8K
Growth Rate:
20.22%
Explore how Flux Dev responds when you change the strengths of layers in the model. See readme for examples of how to select layers.
Total runs:
8.5K
Run Growth:
100
Growth Rate:
1.19%
Ultra high resolution images (up to 4096x4096) based on Stable Cascade
Total runs:
8.1K
Run Growth:
0
Growth Rate:
0.00%
SDXL LCM with multi-controlnet, lora loading, img2img, inpainting
Total runs:
7.1K
Run Growth:
0
Growth Rate:
0.00%
Largest completely open sourced flow-based generation model that is capable of text-to-image generation
Total runs:
6.9K
Run Growth:
500
Growth Rate:
7.25%
A cinematic model fine-tuned on SDXL
Total runs:
6.3K
Run Growth:
100
Growth Rate:
1.59%
Merge two images, with an optional third for controlnet.
Total runs:
5.7K
Run Growth:
200
Growth Rate:
3.51%
An SDXL fine-tune on Apple Vision Pro
Total runs:
5.2K
Run Growth:
0
Growth Rate:
0.00%
Uses 'Align your steps' for faster higher quality images
Total runs:
5.0K
Run Growth:
0
Growth Rate:
0.00%
Merge two images together with a prompt
Total runs:
4.9K
Run Growth:
100
Growth Rate:
2.04%
MusicGen fine-tuned on chamber choir music
Total runs:
4.7K
Run Growth:
100
Growth Rate:
2.13%
Video toolkit – convert, make GIFs, extract audio
Total runs:
4.6K
Run Growth:
100
Growth Rate:
2.17%
An SDXL fine-tune for solid color images
Total runs:
4.5K
Run Growth:
0
Growth Rate:
0.00%
A flux lora trained on a 1980s cyberpunk aesthetic
Total runs:
4.2K
Run Growth:
400
Growth Rate:
9.52%
SDXL fine-tuned on black light imagery
Total runs:
3.8K
Run Growth:
0
Growth Rate:
0.00%
Flux lora trained on Midjourney v3 outputs from 2022, use "a dream, in the style of MJV3" to trigger generation, also try increasing lora strength above 1
Total runs:
3.8K
Run Growth:
0
Growth Rate:
0.00%
Flux lora, use "MNCRFTMOV" to trigger image generation
Total runs:
3.7K
Run Growth:
600
Growth Rate:
24.00%
ZavyChromaXL v7, a high contrast and colorful SDXL fine-tune
Total runs:
3.6K
Run Growth:
0
Growth Rate:
0.00%
Flux lora, use "CLR" to trigger image generation
Total runs:
3.1K
Run Growth:
100
Growth Rate:
3.23%
A realistic, high quality 5 step lightning model
Total runs:
3.0K
Run Growth:
0
Growth Rate:
0.00%
Flux lora, use the term "MNALSA" to trigger generation
Total runs:
3.0K
Run Growth:
200
Growth Rate:
6.67%
SDXL fine-tuned on the people in Toy Story (1995)
Total runs:
2.7K
Run Growth:
0
Growth Rate:
0.00%
Fast video2video with a latent consistency model
Total runs:
2.4K
Run Growth:
0
Growth Rate:
0.00%
SDXL fine-tuned on both Barbie and Tron Legacy
Total runs:
2.0K
Run Growth:
100
Growth Rate:
5.00%
Make pictures of an AI character named 0_1.webp
Total runs:
2.0K
Run Growth:
100
Growth Rate:
5.00%
Flux lora, fine tuned on NEO-1X robot, use "NEO1X" to trigger image generation
Total runs:
1.6K
Run Growth:
0
Growth Rate:
0.00%
SDXL fine-tuned on energy drink designs
Total runs:
1.6K
Run Growth:
0
Growth Rate:
0.00%
Convert a set of frames to a video
Total runs:
1.5K
Run Growth:
0
Growth Rate:
0.00%
A flux dev lora fine-tuned on bad 2004 digital photography
Total runs:
1.5K
Run Growth:
0
Growth Rate:
0.00%
A flux lora fine-tuned to produce handwritten text
Total runs:
1.4K
Run Growth:
930
Growth Rate:
84.55%
A fast high quality SD 1.5 model, Realistic Vision V6.0 B1 Hyper
Total runs:
1.3K
Run Growth:
0
Growth Rate:
0.00%
SDXL fine-tune of Star Trek Next Generation interiors
Total runs:
1.3K
Run Growth:
100
Growth Rate:
7.69%
An SDXL fine-tune based on Deep Dream
Total runs:
1.2K
Run Growth:
0
Growth Rate:
0.00%
SDXL fine-tune based on illustrated cross sections
Total runs:
1.2K
Run Growth:
0
Growth Rate:
0.00%
SDXL fine-tuned on Pixar Cars
Total runs:
1.2K
Run Growth:
0
Growth Rate:
0.00%
Make MS Paint images, a lora trained by aimingfail
Total runs:
1.1K
Run Growth:
100
Growth Rate:
9.09%
👀 SDXL fine-tune to add googly eyes to anything
Total runs:
1000
Run Growth:
0
Growth Rate:
0.00%
Total runs:
950
Run Growth:
38
Growth Rate:
16.38%
SDXL fine-tuned on pareidolia
Total runs:
946
Run Growth:
2
Growth Rate:
0.21%
Exploratory SDXL fine-tuning on text "FOFR"
Total runs:
933
Run Growth:
3
Growth Rate:
0.32%
Flux fine-tuned on JWST deep space astrophotography
Total runs:
932
Run Growth:
30
Growth Rate:
3.22%
A wrapper model for captioning multiple images using GPT, Claude or Gemini, useful for lora training
Total runs:
885
Run Growth:
217
Growth Rate:
24.55%
A flux fine-tune based on neo-impressionism
Total runs:
821
Run Growth:
205
Growth Rate:
26.05%
SDXL fine-tuned on Santa Hats
Total runs:
820
Run Growth:
8
Growth Rate:
0.98%
Flux lora by AggravatingScree7189, use "cyberpunk typeface" to trigger image generation
Total runs:
802
Run Growth:
15
Growth Rate:
1.87%
An SDXL fine-tune based on the Labyrinth movie
Total runs:
797
Run Growth:
0
Growth Rate:
0.00%
Flux lora, use "XSEC cross section" to trigger image generation
Total runs:
793
Run Growth:
12
Growth Rate:
1.51%
Flux lora, use "cassette futurism" to trigger generation
Total runs:
780
Run Growth:
25
Growth Rate:
3.21%
Flux dev lora trained on photos of 1970s food
Total runs:
772
Run Growth:
144
Growth Rate:
18.65%
Tshirt designs with a hidden Replicate logo
Total runs:
711
Run Growth:
3
Growth Rate:
0.42%
Flux lora, trained on macro textures, use "MCROTX" to trigger image generation
Total runs:
683
Run Growth:
22
Growth Rate:
3.22%
Flux lora, use “WRNG” to trigger image generation
Total runs:
650
Run Growth:
0
Growth Rate:
0.00%
An SDXL fine-tune on bad 2048x2048 images
Total runs:
645
Run Growth:
0
Growth Rate:
0.00%
SDXL fine-tuned on Xmas sweaters
Total runs:
614
Run Growth:
0
Growth Rate:
0.00%
Flux lora, use "spitting image caricature" to trigger image generation
Total runs:
599
Run Growth:
30
Growth Rate:
5.01%