Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Autoplay
Run Locally
spiralvideo.zip
6 MB
QRCM_Ref2V_000002000.safetensors
148 MB · SafeTensor · bf16
Download
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<optical-illusion-h3>
About This Model
MINIMAX H3 · LoRAs
Created by
cranpeach
on Civitai
by cranpeach - Optical Illusion Generator (QR Code Monster) LoRa for H3 MiniMax
Creator notes
MiniMax H3 Ref2V Version: Suggested strength: 0.8-1.2 Example prompt: is the source video for the target video edit. 0-4s: is an Optical Illusion video of a bustling forest with sunlight peeking through, attribute_transfer Audio: calming ambient bird chirping outdoor forest Shoutouts to I might be the worst MiniMax H3 Prompter with 8GB VRAM so I would love to see what you all are capable of with decent hardware. This LoRa works but can be finicky and require prompting that points the direction in a specific way, like prompting for fisheye video for the spiral video, or prompting for two lettuce heads for the lettuce bra video. It is trained on tags like turn into a visually striking, high-contrast video of an ocean sunset or sunrise, capturing a dramatic, moody atmosphere while preserving the outlines and shapes of the original video Most of the videos should have their workflow. Tried many things including providing a for the to be based off of but it did not go too well, had better luck describing environments in prompt form. Klein 9B Version: *UPDATE: You can now use this on-site generator - still recommend doing a first pass-through of your image with the turn the image into a black and white stencil against a white background then run that image through this model Suggested strength: 1.0-1.5 Suggested prompt: turn the image into while preserving the outlines and shapes of the original image Basically an Optical Illusion generator using your provided image. You can Usage: I highly suggest editing your input image with the prompt turn the image into a black and white stencil against a white background then run that image through this model. If your image is too human like it will likely just try to generate a human, even if you stencil it. It is very picky about prompt and picture choice as this is not a controlnet but a LoRa. I just checked and my dataset actually contains zero QR codes, so that will be a priority for V2. For tricker images/prompts I suggest fewer steps, higher CFG, higher strength.
Trigger words
<Video 1> is the source video for the target video edit. <Subject 1> is an Optical Illusion video of a bustling forest with sunlight peeking through, attribute_transfer
534 downloads · 50 likes on Civitai
SHA256
5C054C154DF41C1A3DA5F4A35A0A74CE2FD10C1AE520F991DF10FA9C831D3CF6
ModelTrends.ai Model ID
#26938
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler
Steps
8
Size
608x832
Prompt
<Video 1> is the source video for the target video edit. 0-6s: <Subject 1> is an HDR Optical Illusion video of a macro close-up photo of vibrant golden honeycomb dripping with honey while preserving the motion, outlines, and shapes of <Subject 1>, attribute_transfer <Audio 1>: fully_copy - <Audio 1> is reused 1:1 as the target video's complete final audio track. "And you have to do it, you have to or I'll fire you-"
Settings
Sampler
Euler
Steps
8
Size
576x864
Prompt
<Video 1> is the source video for the target video edit. 0-3s: <Subject 1> is an Optical Illusion video of two heads of lettuce sitting on plate removing their outer layers while preserving the motion, outlines, and shapes of <Subject 1>, attribute_transfer <Audio 1>: Audience gasps in confusion and surprise
Settings
Size
640x640
Prompt
subject_definitions: <Video 1> is a reference video: follow its motion and camera work. summary: [reference generation] retention_analysis: <Video 1> (motion and camera work): fully_preserved - the camera work and motion of <Video 1> are retained. detailed_description: [Shot 1] <Video 1> is the source video for the target video edit. <Subject 1> is an Optical Illusion video with a banana in the middle with two melons on the side and a pineapple at the top, glasses have been added on the pineapple, the his lettuce at the bottom of the screen, transfer the motion of the original video. There is only fruit and vegetable on the target video, no skin or human. overall_soundscape: ambient noise. non_diegetic_music: N/A
Settings
Sampler
Euler
Steps
8
Size
608x832
Prompt
<Video 1> is the source video for the target video edit. 0-3s: <Subject 1> is an HDR Optical Illusion video of an outdoor fountain spraying water vertically while preserving the motion, outlines, and shapes of <Subject 1>, attribute_transfer <Audio 1>: fully_copy - <Audio 1> is reused 1:1 as the target video's complete final audio track.
Settings
Sampler
Euler
Steps
8
Size
544x928
Prompt
<Video 1> is the source video for the target video edit. 0-6s: turn <Subject 1> into a fisheye Optical Illusion video of a photorealistic town with intricate patterned moving clouds and winding roads while preserving the motion, outlines, and shapes of <Subject 1>, attribute_transfer attribute_transferAudio: ambient outdoor noises
Settings
Sampler
Euler
Steps
8
Size
576x864
Prompt
<Video 1> is the source video for the target video edit. 0-4s: <Subject 1> is an Optical Illusion video of a wavy ocean at sunset background, attribute_transfer <Audio 1>
Settings
Size
544x928
Prompt
<Video 1> is the source video for the target video edit. 0-6s: turn <Subject 1> into a fisheye Optical Illusion video of a photorealistic town with intricate patterned moving clouds and winding roads while preserving the motion, outlines, and shapes of <Subject 1>, attribute_transfer attribute_transferAudio: ambient outdoor noises
AI Models for Image, Video & Text Generation
optical illusion h3 is a LoRA for the MiniMax H3 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other MiniMax H3 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models