AlekseyCalvin/Neureal_Merge_v1_Flux_LoRA_By_SilverAgePoets

Prompt

RCA style agitprop poster, Neurealist textographic photo collage, MAYAK style art by Mayakovsky

Prompt

film photograph portrait RCA style agitprop poster, Neurealist textographic photo collage, MAYAK style art by Mayakovsky

Prompt

text: RCA style agitprop poster, Neurealist textographic photo collage, MAYAK style art by Mayakovsky

Prompt

high definition award winning intricate dynamic photorealistic close up photo portrait of RCA style agitprop poster, Neurealist textographic photo collage, MAYAK style art by Mayakovsky

Prompt

high definition award winning intricate dynamic photorealistic close up photo portrait of RCA style agitprop poster, Neurealist textographic photo collage, MAYAK style art by Mayakovsky

NEUREAL MERGE FLUX LoRA for Posters, Illustrations, Book Covers, Collage art, Pamphlets, and more. By SilverAgePoets.com

For this LoRA we merged several of our rank-64 LoRAS trained on DeDistilled Flux models. Namely, we combined two of the Neurealist Collage models, one of the Mayakovsky & Rodchenko art style models, and one of our RCA models. Consequently, this LoRA is surely very biased towards Communist iconography.

Alas, the merging process we used (one of Kohya's sd-scripts) forcedly excised the text encoder tuned layers from the models, which may have undercut ( at least here specifically) whatever progress we may have otherwise made with longer phrase rendering consistency. But we will see. In some other ways, this LoRA seems to actually respond more stably than some of its components...

Trigger words

You should use RCA style or/and MAYAK style or/and Neurealist textographic photo collage` to summon the poet's latent spirit.

Use it with the 🧨 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/Neureal_Merge_v1_Flux_LoRA_By_SilverAgePoets', weight_name='NeurealMerge.safetensors')
image = pipeline('your prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers