PONY CLIP 100k Finetune
JoyCLIP is a further advancement of this CLIP
Note this is still a great base to start a finetune of PONY CLIP as the gradient was 50 out. Starting with this model you will be in the 4-8 range.
100k is a full finetune of base pony CLIP-L and CLIP-G
100k can be used in any model base V6, Autism, Anime or Realistic (Even non-pony SDXL Models)
CLIP-G took 68GB and 30 hours to train.
Forge users, you will need to download Comfy UI as CLIP replacement is only supported for FLUX, this may apply to Auto 1111 also. Once a model is saved with replaced clip it can be used in Forge or Auto
Can be run in any UI (Forge, Auto1111, Comfy UI) the model will be downcast by default. These settings improve complexity but are not required. (Full FP32 is not recommended but FP32 CLIP is)
Comfy UI --fp32-text-enc OR --force-fp32
Forge/Auto1111 --clip-in-fp32 OR --all-in-fp32
Description
FAQ
Comments (10)
I'm going to test!
Sounds good, it needs LORA testing for SDXL and PONY based for sure
@Felldude Can you share someone prompt guide?
@megachina31687 It would be the same as Base Pony v6, score, characters are all the same
What exatly are the differences between this and base?
1,000,000 zeros have been restored (Precision attention to detail) the CLIP has been restored
@Felldude Ok! In practice what does it mean?
I mean there are realistic pics in your samples, i didnt know base Pony is capable for that.
@sukhmanpatton839 I don't think I can explain it any more simply, try a video on FP16 vs FP32
@sukhmanpatton839 I just put a super realistic model in EA but it will be free by christmas
Details
Files
ponyCLIP100kFinetune_basev6CheckpointFP32.safetensors
Mirrors
fp32PonyV6OneMillionBlock_basev6CheckpointFP32.safetensors
fp32PonyV6OneMillionBlock_ponyCheckpointFP32.safetensors
fp32PonyV6OneMillionBlock_ponyCheckpointFP32.safetensors
fp32PonyV6OneMillionBlock_basev6CheckpointFP32.safetensors
fp32PonyV6OneMillionBlock_basev6CheckpointFP32.safetensors
fp32PonyV6OneMillionBlock_basev6CheckpointFP32.safetensors
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.










