Find what you need for your workflow.

LFM2 Audio 1.5B

lfm1.0

Ministral 3 14B Reasoning 2512 Uncensored GGUF

GGUF quantized versions of Ministral-3-14B-Reasoning-2512-Uncensored, a fine-tuned version of Ministral-3-14B-Reasoning-2512 with uncensored responses.

ip-adapter-faceid-plusv2

we use LoRA to improve ID consistency. IP-Adapter-FaceID can generate various style images conditioned on a face with only text prompts.

FLUX.1 [dev] fp8 versions - Scaled fp8/fp8_e4m3fn/fp8_e5m2

I've added some other fp8 versions of FLUX.1 [dev] that aren't hosted on Civitai anymore, specifically fp8e4m3fn and fp8e5m2, in addition to the scaled fp8 FLUX.1 [dev] version I had originally posted.

Qwen2 0.5B GRPO Test

This model is a fine-tuned version of Qwen/Qwen2-0.5B-Instruct. It has been trained using TRL.

Convlstm 8 2026 07 12

This model has been pushed to the Hub using the PytorchModelHubMixin integration: Code: [More Information Needed] Paper: [More Information Needed] Docs: [More Information Needed]

X3N0 Flux

Si des Francais veullent nous rejoindre sur un discord :

2727829

Exact lora artifact distributed with Krea 2 - Enable NSFW prompt adherence (krea2 nsfw) (v1.0).

LCM-LoRA SDXL

An SDXL LoRA adapter that enables Latent Consistency Model inference in roughly two to eight denoising steps.

MS Z-Image Turbo

This is my version of Z Image Turbo.

Rhodochrosite World Morph | Illustrious (v1.0)

Co147

Co172

Pid Flux2

nvidia-license

FLUX.Fill-dev(gguf)

🌊 FLUX.1-Fill-dev Quantized: Advanced Diffusion for Seamless Image Editing

FLUX.2 Klein 4B INT8 ConvRot

flux-non-commercial-license

NexBlendMix aurora Asian Semi Realistic - SD1

[NexBlendMixaurora] Korean Semi-Realistic SD 1.5 Model