News and site search

flux-text-encoders

The two text-encoder files FLUX.1 needs to run under stable-diffusion.cpp, mirrored from comfyanonymous/flux_text_encoders. Unsloth Studio fetches these on the no-GPU (native sd.cpp) path. It used to fetch them straight from the community repack; nobody there owes anyone availability, and a rename or a takedown turns every CPU FLUX.1 load into a 404. So they are mirrored here. **The weights are unmodified:** byte for byte the files of the same name in the source repo. Only these two files are mirrored. The source repo also ships fp8 T5 variants; Studio does not use them, so they are not here.

Qwen-Image-2.1-Turbo-Uncensored-GGUF

Qwen-Image's text encoder, Qwen3-VL-8B-Instruct, with its refusal direction projected out: a drop-in --llm for stable-diffusion.cpp next to our Turbo denoiser GGUFs . Below, exactly which part is uncensored and what that does to the pictures. The measurements are public. As a chat model, the encoder's refusals fall from 88.9% to 1.2% on held-out English prompts. MMLU is unchanged: 77.35% before and after. On images it changes nothing we could measure. The stock Qwen-Image pipeline has no filter and already draws all 9 sensitive categories we tested, and with this encoder not one of 45 prompts changed outcome. See where exactly this is uncensored . Generate images locally in Atomic Chat . It runs stable-diffusion.cpp, the engine these files were built and checked with. Qwen-Image 2.1 makes a picture with three parts. Only one of them is changed here.

MagicPrompt-Stable-Diffusion

This is a model from the MagicPrompt series of models, which are GPT-2 models intended to generate prompt texts for imaging AIs, in this case: Stable Diffusion. This model was trained with 150,000 steps and a set of about 80,000 data filtered and extracted from the image finder for Stable Diffusion: "Lexica.art". It was a little difficult to extract the data, since the search engine still doesn't have a public API without being protected by cloudflare, but if you want to take a look at the original dataset, you can have a look here: datasets/Gustavosta/Stable-Diffusion-Prompts. If you want to test the model with a demo, you can go to: "spaces/Gustavosta/MagicPrompt-Stable-Diffusion".

stable-diffusion-v1-5

stable-diffusion-v1-5

marigold-depth-v1-1

This is a model card for the `marigold-depth-v1-1` model for monocular depth estimation from a single image. The model is fine-tuned from the `stable-diffusion-2` model as described in our papers: - CVPR'2024 paper titled "Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation" - Journal extension titled "Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis"

stable-diffusion-3.5-controlnets

stable-diffusion-3.5-medium_amdgpu

stable-diffusion-xl-1.0-tensorrt

stable-diffusion-2-1-base

This model card focuses on the model associated with the Stable Diffusion v2-1-base model. This `stable-diffusion-2-1-base` model fine-tunes stable-diffusion-2-base (`512-base-ema.ckpt`) with 220k extra steps taken, with `punsafe=0.98` on the same dataset. - Use it with the `stablediffusion` repository: download the `v2-1_512-ema-pruned.ckpt` here. - Use it with 🧨 `diffusers`