Edit model card

EclecticEuphoria_Flux_Unet_Schnell_v2

A much improved version with a constant ability to reproduce better consistant images. Q6 and Q4 models produce much better images out of the gate now. Does NSFW, but with the typical flux anatomy issues, if you struggle with flux not wanting to do NSFW try adding "exposed (breast:2.0), (Nipples:2.0)" You will need the Vae and Dual Clip as these are unet models.

EclecticEuphoria_Flux_Unet_Schnell_v2-f16.safetensors

EclecticEuphoria_Flux_Unet_Schnell_v2-Q8_K.gguf

EclecticEuphoria_Flux_Unet_Schnell_v2-Q6_K.gguf

EclecticEuphoria_Flux_Unet_Schnell_v2-Q4_K.gguf

GGUF Q8 - refinded and upscaled

GGUF Q6 - refinded and upscaled

GGUF Q4 - refinded and upscaled

Link below are more images - the latest, most upper ones

Civitai Gallery of Schnell Images from this model


EclecticEuphoria_Flux_Unet_Schnell_models (Initial Release)

Not of a huge fan of Schnell on first use so I took up a challenge to remove what I didn't like of Schnell. First goal was to remove the hideous Greenish blotchy look and the random dark splotches all over. I used lora and thanks to the negative field was able to remove most of those issues and get a more natural looking image. So I am calling this version a win. The standard model produces much better images out of the gate vs the ggufs. A refiner is definately needed in both cases, the ggufs are complete rubish looking straight out of the sampler, but it's a good thing as the noise gives the refiner something good to work with. So find a favorite refiner model and plug it in for best results. Images are created in 8 steps. I only tested the 8_0K gguf a couple times, not sure how well the K6 and K4 models do. I do like the artsy style of schnell tho, it can really produce some unique beatuiful pictres in a hurry.

Standard Workflow

GGUF Workflow

Standard Comparison sampler vs refine

Standard

GGUF Q8

Standard with controlnet

Link below are more images - the latest, most upper ones

Civitai Gallery of Schnell Images from this model

Downloads last month
73
GGUF
Model size
11.9B params
Architecture
flux

4-bit

6-bit

8-bit

Inference API
Unable to determine this model's library. Check the docs .