Instructions to use AlekseyCalvin/RCA_Agitprop_Flux_LoRA_v2.5_on_Shuttle3Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AlekseyCalvin/RCA_Agitprop_Flux_LoRA_v2.5_on_Shuttle3Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AlekseyCalvin/Colossus_2.1_dedistilled_by_AfroMan4peace", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("AlekseyCalvin/RCA_Agitprop_Flux_LoRA_v2.5_on_Shuttle3Diffusion") prompt = "RCA style agitprop communist poster..." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Version 2.5 of our Agitprop Graphics/Art-generating Low-Rank Adapter (LoRA) for Flux-based text2image model.
Made for the use of the Revolutionary Communists of America (RCA) (CommunistUSA.org).

- Prompt
- RCA style agitprop communist poster...
This iteration here is another parallel test release, fine-tuned over a De-distilled Flux-based Checkpoint different from the underlying bases of Version 2/2.1 (Colossus 2.1), 2.3 (Genova APEX), and 1.0 (regular Flux Dev) alike.
This version, which we've numbered 2.5, was fine-tuned over the newly released Shuttle 3 Diffusion by ShuttleAi), an especially compelling and thus far promising fully open-source modification of Flux Schnell.
- Downloads last month
- 16
Model tree for AlekseyCalvin/RCA_Agitprop_Flux_LoRA_v2.5_on_Shuttle3Diffusion
Base model
black-forest-labs/FLUX.1-dev