Precise Flux dev NF4 FP8/FP16 | CLIP and VAE included - v1.0 fp8
Prompt Negativi Consigliati
ugly, deformed, noisy, blurry, distorted, out of focus
Parametri Consigliati
samplers
steps
cfg
resolution
vae
other models
Suggerimenti
For best results with LoRAs in Forge, select in Diffusion in Low Bits: Automatic (fp16 LoRA).
In Forge, choose Euler or Flux Realistic samplers with Schedule type: Simple.
Punti Salienti della Versione
This model is converted to bnb nf4 by mixing Flux dev fp8 with VAE, text encoder T5xxl-fp8 and Clip-l. All included!
Sponsor del Creatore
Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license.
This model is converted to bnb nf4 by mixing Flux dev fp8 with VAE, text encoder T5xxl-fp8 and Clip-l. All included!
For those who don't care about size, also blended full dev fp16 with VAE, text encoder T5xxl-fp16 and Clip-l in NF4. All included!
From many observations, the FP8 is a bit more accurate in understanding the prompt. And having assembled this build and tested it, I came to the same conclusion.
This model is a bit more accurate than the familiar NF4 v2. I've done a lot of generation with complex prompts to assert this. And I am completely satisfied with the way this model understands me. With simple prompts I didn't notice any difference.
The model works well with lors in Forge, in which I create in. Don't forget to select in Diffusion in Low Bits: Automatic (fp16 LoRA).
In Forge I choose Euler or Flux Realistic samplers, Schedule type: Simple. CFG: 1, number of steps 20-30.
Generated outputs can be used for personal, scientific, and commercial purposes as described in the flux-1-dev-non-commercial-license
Dettagli del Modello
Tipo di modello
Modello base
Versione del modello
Hash del modello
Creatore
Discussione
Per favore log in per lasciare un commento.