Hugging Face's logo

silveroxides
/
FLUX.2-dev-fp8_scaled

Image-to-Image
Diffusion Single File
English
image-generation
image-editing
flux
comfyui
fp8_scaled
Model card Files
xet
 Community
15
silveroxides commited on
Commit
8c3c0b1
·
verified ·
1 Parent(s): 8aa0308

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -21,13 +21,15 @@ tags:
21
  pipeline_tag: image-to-image
22
  ---
23
 
 
24
  ## You can find workflow with samples in the [workflow_assets](https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/tree/main/workflow_assets) folder.
25
 
26
  ### The [workflow](https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/blob/main/workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-workflow.json) contains the information and links needed to get started with using this model.
27
  ### This fp8_scaled model is faster than the official one released by ComfyOrg when used with the Loader in the workflow.
28
  ### The custom node that loads the model in the workflow is necessary to obtain fastest inference on lower VRAM GPU.
29
 
30
- ### If you want to use the int8 model, then you need to use [silveroxides/ComfyUI-QuantOps](https://github.com/silveroxides/ComfyUI-QuantOps) custom node until official support is merged.
 
31
 
32
  ![Workflow](./workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-overview.png)
33
 
 
21
  pipeline_tag: image-to-image
22
  ---
23
 
24
+
25
  ## You can find workflow with samples in the [workflow_assets](https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/tree/main/workflow_assets) folder.
26
 
27
  ### The [workflow](https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/blob/main/workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-workflow.json) contains the information and links needed to get started with using this model.
28
  ### This fp8_scaled model is faster than the official one released by ComfyOrg when used with the Loader in the workflow.
29
  ### The custom node that loads the model in the workflow is necessary to obtain fastest inference on lower VRAM GPU.
30
 
31
+ ### If you want to use mxfp8, then you need to use [silveroxides/ComfyUI-QuantOps](https://github.com/silveroxides/ComfyUI-QuantOps) custom node and custom custom comfy-kitchen [Repo with instructions](https://huggingface.co/silveroxides/Chroma1-HD-fp8-scaled/tree/main/experimental) until official support is merged.
32
+ ### Use [BobJohnson24/ComfyUI-Flux2-INT8](https://github.com/BobJohnson24/ComfyUI-Flux2-INT8) for int8 tensorwise model.
33
 
34
  ![Workflow](./workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-overview.png)
35