Downloads · 30 days
48
11% of all-time downloads
AlekseyCalvin/Neureal_Merge_v1_Flux_LoRA_By_SilverAgePoets
Neureal_Merge_v1_Flux_LoRA_By_SilverAgePoets is a text-to-image model from AlekseyCalvin. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
48
11% of all-time downloads
All-time downloads
421
Public
Repo size
2.2 GB
Likes
1
Public
Click a slice to open those files.
.safetensors2.2 GB · 100%
From the Hugging Face model README
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...
You should use RCA style or/and MAYAK style or/and Neurealist textographic photo collage` to summon the poet's latent spirit.
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