%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Hstcolorflux LushApparitionLoRAII
H
Hstcolorflux LushApparitionLoRAII
Developed by AlekseyCalvin
A LoRA adapter based on Flux.1-dev, specializing in generating high-quality color images with historical photography styles
Downloads 39
Release Time : 4/2/2025
Model Overview
This LoRA adapter fine-tunes specific layers of the Flux base model to generate vivid images with early 20th-century color photography styles (inspired by Sergei Prokudin-Gorsky's works), featuring a surreal artistic tendency
Model Features
Historical Photography Style
Inspired by pioneering works of early 20th-century color photography, generating images with unique historical textures
Creative Freedom
Treats text prompts as non-mandatory suggestions, often producing unexpected surreal artistic effects
Shallow Intervention
Only performs shallow fine-tuning on the base model yet achieves significant stylistic effects
Advanced Configuration
Uses special parameter settings optimized for specific layers/components rather than common surface feature adaptations
Model Capabilities
Text-to-Image Generation
Historical Style Image Generation
Surreal Art Creation
Photorealistic Image Generation
Use Cases
Artistic Creation
Historical Style Photography
Generates images with early 20th-century color photography styles
Images with distinct tendencies toward modern art museum photography styles
Surreal Art
Generates surreal otherworldly creatures and scenes from mundane prompts
Surreal images with aesthetic tension
š HSToric Color Lush Apparition V.2 Low-Rank Adapter
This project is a low-rank adapter that aims to redefine the concept of "quality" in photorealistic inference using Flux variants. It draws inspiration from historical color photography, producing aesthetically compelling and sometimes phantasmagoric imagery.
š Quick Start
Trigger words
You should use HST style autochrome photograph to open a vivid window into a chromatically bewitching ever-futurous past.
Use it with the š§Ø diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('AlekseyCalvin/HSTcolorFlux_LushApparitionLoRAII')
image = pipeline('your prompt').images[0]
āØ Features
- Innovative Training Approach: Our two HSToric Color Lush Apparition low-rank adapter series are byproducts of early Flux training experiments in summer 2024. We aimed to reposition the concept of "quality" in photorealistic inference using open/distilled Flux variants, especially Schnell. We turned to the archival legacy of Sergey Prokudin - Gorsky's 3 - color - composite photography technique from the 1900s - 1910s.
- Unique Prompt Response: Lush Apparition Version 2 approaches text prompts as vague suggestions. However, the imagery it produces is aesthetically compelling and often photorealistic, with a bias towards art - gallery - worthy photography. It can even create phantasmagoric creatures and scenes from simple prompts.
- Sibling Adapter Characteristics: Its sibling, Lush Apparition Version 1, takes prompts well and sometimes adds surprising spins.
- Related LoRAs: There are other successful LoRAs in the HSToric Color series, such as HSToric Color Dedistilled, HSToric Color Schnell, HSToric FOCUS, HSToric Color SD3.5L V.1.
- Text - to - Video Additions: New Text - to - Video LoRAs in the HSToric Color series include HSToric Color Film WAN14B v1 (Rank 256), HSToric Color Film WAN1.3B v2 (Rank 128), HSToric Color Film WAN1.3B v1 (Rank 32).
š License
This project is licensed under the Apache - 2.0 license.
š Documentation
Model Information
| Property | Details |
|---|---|
| Model Type | Low - Rank Adapter for text - to - image generation |
| Base Model | black - forest - labs/FLUX.1 - dev |
| Pipeline Tag | text - to - image |
| Instance Prompt | HST style autochrome photograph, colorful vibrant |
Gallery
Here are some example outputs with their corresponding prompts: | Prompt | Output Image | |--------|--------------| | History proceeding in screams of cold metal criss - crossing a world heavy with desperate deserters; stacked strawy wigs & hats, shoveling coal unto alivetimeās horizons. In reply, signals sproutā¦ Looming, hurtling through trees, out of the darkā¦ trembling, skating in on the spectacleās marionette arksā¦ rafting over imagery on a constructivist frame, surviving on abstract elements, grafted everyplace, graphically, grifters juggling coals, climbing out of a tomb of long - ago cremated air, splashing around cherry juice from shot - thru chests, no longer just any bleeding hearts, but alivetimeās horizon | [example_ide38v1le.png](images/example_ide38v1le.png) | | HST autochrome photo reels of a close up History proceeding dawnless machinized thru screams of cold metal criss - crossing a disowned world of rentiers heavy with desperate deserters; stacked strawy wigs & hats, shoveling coal towards voracious camera eyes unto alivetimeās horizons. In reply, signals sproutā¦ Brandishing tools of war... Looming, hurtling through trees, out of the darkā¦ trembling, skating in on the spectacleās marionette arksā¦ rafting over imagery on a constructivist frame, surviving on abstract elements, grafted everyplace, graphically, grifters juggling coals, climbing out of a tomb of long - ago cremated air, splashing around cherry juice from shot - thru chests, no longer just any bleeding hearts, but alivetimeās horizons reconfiguring | [example_w8woqfju1.png](images/example_w8woqfju1.png) | | HST autochrome photo reels oHistory proceeding in screams of cold metal criss - crossing a world heavy with a wild diversity of desperate photorealistic deserters; meanwhile, in tacitly dimensioned ghosty borders, our time schedulers get re - engineered by an enthusiast, āKonstantin Ivanovā, a sortova Lenin disguised in stacking strawy wigs & hats, onto their flaps & caps jerry - rigged cyber - limbs quickly shoveling dialectically - synthesized coal unto alivetimeās horizons. In reply, signals sproutā¦ Looming, hurtling through trees, out of the darkā¦ diffusely trembling, skating in on hybrid spectacles' marionette arksā¦ else, drifting over bottomless cosmic - size imagery basins, rafting in on brane - like constructivist frames fed on abstractions manually snapped & stuffed into rear - end perked transparent pipelines, from frontal breath - holes spewing everyplace, graphically, or juggled as coals, Guy Debord grins, climbing out of a tomb of long - ago cremated air, splashing around cherry juice from a shot - thru chest, no longer a bleeding heart, but alivetimeās horizon, diversities of characteristics, face galleries, candid human catalogues shot on cell phones and pinned unto proto - historical musing walls like the wingy pattern corpses of Nabokovian butterflies | [example_m92fwfu87.png](images/example_m92fwfu87.png) | | HST style autochrome horror analog IMG_1099.CR2 film photograph of 1917 Petrograd during the October revolution with twelve bolshevik red guards walking through snowy avenues at night in a wild windy blizzard, text caption: snowstorm, snowbanks, starved miserable hound dog drags behind them with tail tucked, the guards have rifles over shoulders, blemished wrinkled textured faces, expressionist horror, expressive, aiming at phantom scary shadows around phantasmagoric avenues and snowbanks, text caption: IMG_1004.CR2 kodachrome | [example_wj6jh3ys2.png](images/example_wj6jh3ys2.png) | | HST style autochrome collage featuring two distinct sections. bright vivid colors, contrast fix, color corrected, The upper section shows a silhouetted portrait of a figure in a suit, set against a vivid background with swirling clouds and a caption referencing a 1906 post - impressionist painter, which reads: "a true post - impressionist painter once confessed to Paul Sean... we live in a rainbow, she said. Agape, Paul lost face." Obviously, this is why the central subject of this image is missing a face. The bottom section features a hand - drawn subject all agape with panic (and whose appearance was adapted from Munsch's "The Scream"). Here, the subject screasm in a huge garden of building - like 3D obelisks, while the title text above this image asks: "Why SO CONFUSED?" and the key symbolic message, appearing as a textual overlay, answers the above question with: "you're seeing... (that) what you're reading is.../ not what's.../ you". This caption neatly explains the screamer's panic. The screamer is actually Paul Sean from the upper image. In the bottom section we get to see his face, which has gotten a bit more than merely lost. The composition as a whole blends art styles, textual elements, and vibrant colors, creating a visually striking and complex composition. The lower section resembles the famous painting "The Scream" in a surreal landscape of jagged, colorful forms. | [example_v4ne83f9w.png](images/example_v4ne83f9w.png) | | HST style layered see - through translucent transparent photorealistic vivid color photo . an HD photograph of Real Timothy, a fleshless creature of organs, veins, arteries, bones, and a skull - less brain, climbs over the page border towards a 1915 lighthouse, amid a psychedelic wonderland | [example_34xtdr4ve.png](images/example_34xtdr4ve.png) | | HST style photo of planet Earth as seen from space, over it floats a blooming fantastic utopian space station lush vibrant space city shaped and styled as the rainbow flag of the LGBTQ+ community and a crimson red hammer and sickle over it, from down below, a red hammer and sickle appearing to be waving with it sickle limb towards the rainbow and black hammer and sickle above it. | [example_tb9gr9m29.png](images/example_tb9gr9m29.png) | | HST style autochrome photo close up of androgynous cute guitarist screaming with the muffled voice storm of every erstwhle possible personout of the collective hyper - proletarianized toilet of platform feudalism | [example_3igt7pguk.png](images/example_3igt7pguk.png) | | HST style autochrome photo close up of androgynous scholar screaming with the muffled voice storm of every erstwhle possible personout of the collective hyper - proletarianized toilet of platform feudalism | [example_62fiylm57.png](images/example_62fiylm57.png) | | HST style autochrome photo close up of a gothy punky young woman wielding a baseball bat and angrily cathartically smashing bashing breaking with it the windows of department stores and cars in a plaza parking lot at night. She has pink hair in a messy shortish punky haircut. Amid the desolate morbid consumerist undead sprawl of California. Grungy eerie iconic mysterious radical ambience | [example_50nlcjof2.png](images/example_50nlcjof2.png) | | HST style autochrome photo close up of a gothy punky young woman wielding a baseball bat and angrily cathartically smashing bashing breaking with it the windows of department stores and cars in a plaza parking lot at night. She has pink hair in a messy shortish punky haircut. Amid the desolate morbid consumerist undead sprawl of California. Grungy eerie iconic mysterious radical ambience. Pink hair. Pink. Pink. | [example_diicoutdi.png](images/example_diicoutdi.png) | | HST style IMG_1099.CR2 photo close up of a gothy punky young woman wielding a baseball bat and angrily cathartically smashing bashing breaking with it the windows of department stores and cars in a plaza parking lot at night. analog. Close - up detailed IMG_1099.CR2 film photograph.She has pink hair in a messy shortish punky haircut. Amid the desolate morbid consumerist undead sprawl of California. Pink hair. Angry. Shot on a cell phone. Grungy eerie iconic mysterious radical ambience | [example_we90v3vce.png](images/example_we90v3vce.png) | | HST style photo close up detailed IMG_1099.CR2 film photograph of a tall thin male smiling skeleton guy with medium - length black hair parted in the middle close up on face with raised eyebrows and one finger raised, with a wilting flower covered and hidden by tiny swirling tornado of rainclouds wrapping around the raised finger and twisting around the flow obscuring it. Amid the morbid consumerist undead sprawl of California. In a desolate outdoor shopping mall parking lot at night. Shot on a cell phone. Grungy eerie iconic mysterious radical ambience. | [example_y9r267qsk.png](images/example_y9r267qsk.png) | | HST style photo close up detailed IMG_1099.CR2 film photograph of a tall thin male smiling skeleton guy with medium - length black hair parted in the middle close up on face with raised eyebrows and one finger raised, with a wilting flower covered and hidden by tiny swirling tornado of rainclouds wrapping around the raised finger and twisting around the flow obscuring it. Amid the morbid consumerist undead sprawl of California. In a desolate outdoor shopping mall parking lot at night. Shot on a cell phone. Grungy eerie iconic mysterious radical ambience. Skeleton. Skeleton. Skeletal. Skeleted. Skelet. Skeletalized. Undead scull and living bones. Defleshed fellow. Fleshless skeletal subject. | [example_pzhrgyapp.png](images/example_pzhrgyapp.png) |
Stable Diffusion V1 5
Openrail
Stable Diffusion is a latent text-to-image diffusion model capable of generating realistic images from any text input.
Image Generation
S
stable-diffusion-v1-5
3.7M
518
Stable Diffusion Inpainting
Openrail
A text-to-image generation model based on stable diffusion with image inpainting capabilities
Image Generation
S
stable-diffusion-v1-5
3.3M
56
Stable Diffusion Xl Base 1.0
SDXL 1.0 is a diffusion-based text-to-image generation model that employs an expert-integrated latent diffusion process, supporting high-resolution image generation
Image Generation
S
stabilityai
2.4M
6,545
Stable Diffusion V1 4
Openrail
Stable Diffusion is a latent text-to-image diffusion model capable of generating realistic images from any text input.
Image Generation
S
CompVis
1.7M
6,778
Stable Diffusion Xl Refiner 1.0
The SD-XL 1.0 Refiner Model is an image generation model developed by Stability AI, designed to enhance the quality of images generated by the SDXL base model, with particular expertise in the final denoising step.
Image Generation
S
stabilityai
1.1M
1,882
Stable Diffusion 2 1
A diffusion-based text-to-image generation model that supports image generation and modification through text prompts
Image Generation
S
stabilityai
948.75k
3,966
Stable Diffusion Xl 1.0 Inpainting 0.1
A latent text-to-image diffusion model based on Stable Diffusion XL, capable of image inpainting via masks
Image Generation
S
diffusers
673.14k
334
Stable Diffusion 2 Base
Diffusion-based text-to-image model capable of generating high-quality images from text prompts
Image Generation
S
stabilityai
613.60k
349
Playground V2.5 1024px Aesthetic
Other
An open-source text-to-image model capable of generating aesthetic images at 1024x1024 resolution and various aspect ratios, leading in aesthetic quality within the open-source domain.
Image Generation
P
playgroundai
554.94k
723
Sd Turbo
SD-Turbo is a high-speed text-to-image model capable of generating realistic images from text prompts with just a single network inference. Released as a research prototype, it aims to explore compact distilled text-to-image models.
Image Generation
S
stabilityai
502.82k
380
Featured Recommended AI Models
Ā© 2025AIbase