--- title: renderartist-weirdthingsflux canonical_url: "https://www.modelscope.cn/models/hf/renderartist-weirdthingsflux" md_url: "https://www.modelscope.cn/models/hf/renderartist-weirdthingsflux.md" repository: hf/renderartist-weirdthingsflux last_updated: 2025-12-04 license: creativeml-openrail-m pipeline_tag: text-to-image-synthesis tasks: - text-to-image-synthesis base_model: - black-forest-labs/FLUX.1-dev base_model_relation: adapter parameters: 114.9M tensor_type: - BF16 library_name: - lora - diffusers - safetensors - pytorch frameworks: - pytorch downloads: 57 stars: 0 tags: - text-to-image - lora - diffusers - "template:diffusion-lora" --- # renderartist-weirdthingsflux > renderartist-weirdthingsflux - hf 在 ModelScope 开源的模型。Weird Things Flux was trained on 100 AI-generated images. This LoRA blends styles of surrealism and psychedelia. In my testing it performed well with both simple and detailed prompts. You should try using… hf/renderartist-weirdthingsflux 是 ModelScope 魔搭社区上的 114.9M 参数text-to-image-synthesis模型，采用 creativeml-openrail-m 许可，基于 black-forest-labs/FLUX.1-dev 构建。 - **Repository**: hf/renderartist-weirdthingsflux - **License**: creativeml-openrail-m - **Tasks**: text-to-image-synthesis - **Parameters**: 114.9M - **Base model**: black-forest-labs/FLUX.1-dev - **Tags**: text-to-image, lora, diffusers, template:diffusion-lora - **Downloads**: 57 - **Stars**: 0 - **Last updated**: 2025-12-04 Source: https://www.modelscope.cn/models/hf/renderartist-weirdthingsflux --- # Weird Things Flux ## Model description Weird Things Flux was trained on 100 AI-generated images. This LoRA blends styles of surrealism and psychedelia. In my testing it performed well with both simple and detailed prompts. You should try using an LLM to describe an existing piece to find words to describe the style you're looking to achieve, some of the examples have lengthy prompts to show the strength of more precise verbiage. All of the images were captioned with Joy Caption Batch 100 images, 1 repeats, 2 batch, 25 epochs, 24 DIM / 32 ALPHA, 1,250 steps This isn't a very serious LoRA, have fun, flex your creativity and make something interesting. This is just an attempt to explore finer details and more ambiguous styles in LoRA training. FOR THE BEST RESULTS USE EULER OR DEIS SAMPLER Trigger keyword: 'w3irdth1ngs' 'illustration' Recommended strengths: 0.7 - 0.9 ## Trigger words You should use `w3irdth1ngs` to trigger the image generation. You should use `illustration` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/renderartist/weirdthingsflux/tree/main) them in the Files & versions tab.